基于神经场逆渲染的三维重建研究综述

doi:10.11996/JG.j.2095-302X.2026030449

图学学报 ›› 2026, Vol. 47 ›› Issue (3): 449-471.DOI: 10.11996/JG.j.2095-302X.2026030449

基于神经场逆渲染的三维重建研究综述

周雪杨¹^,², 沈旭昆²^,³, 胡勇²^,³()

¹ 北京航空航天大学计算机学院，北京 100191
² 智能创意内容生成与沉浸体验北京市重点实验室，北京 100191
³ 北京航空航天大学新媒体艺术与设计学院，北京 100191

收稿日期:2025-10-27 接受日期:2026-01-28 出版日期:2026-06-30 发布日期:2026-06-30
通讯作者:胡勇，E-mail：huyong@buaa.edu.cn
基金资助:
面向云南非遗的虚实融合沉浸体验与传播设计研究(2024KSGCZX001);云南省高校民族文化数字媒体与动漫创意设计工程研究中心(云南艺术学院)开放课题

A review of research on 3D reconstruction based on neural field inverse rendering

ZHOU Xueyang¹^,², SHEN Xukun²^,³, HU Yong²^,³()

¹ School of Computer Science and Engineering, Beihang University, Beijing 100191, China
² Beijing Key Laboratory of Intelligent Creative Content Generation and Immersive Experience, Beihang University, Beijing 100191, China
³ School of New Media Art and Design, Beihang University, Beijing 100191, China

Received:2025-10-27 Accepted:2026-01-28 Published:2026-06-30 Online:2026-06-30
Contact: HU Yong，E-mail：huyong@buaa.edu.cn
Supported by:
Research on Immersive Experience and Communication Design of Virtual-Reality Fusion for Intangible Cultural Heritage in Yunnan(2024KSGCZX001);Open Project of Yunnan Provincial University Engineering Research Center for Digital Media and Animation Creative Design of Ethnic Culture (Yunnan Arts University)

摘要/Abstract

摘要：

在计算机视觉与计算机图形学中，三维重建旨在从二维图像、视频或其他传感器数据生成真实物体/场景的高精度数字模型，长期受到学术界与工业界关注。近年来，深度学习推动三维重建在精度与效率上持续提升，并服务于重光照、数字孪生和虚拟现实等应用。随着神经辐射场(NeRF)的提出，基于神经场的重建逐渐成为主流；为提升外观解耦能力，逆渲染被引入并形成较完整的重建框架。针对该领域的研究数量庞大且技术路线分散、缺少系统梳理的问题，本文面向静态物体与场景，按流程将基于神经场逆渲染的三维重建划分为2部分：基于神经场的表面重建，以及基于神经场的材质光照估计。并围绕2部分提炼核心研究问题，以“研究问题-技术方案”的思路对主流方法进行归纳与对比，逐项分析其关键原理与推导过程，以启发后续算法设计。此外，整理了2个方向常用的数据集与评价指标，并讨论其细节与适用性。最后，总结了未来值得继续关注的挑战与可行思路的展望。

关键词: 三维重建, 神经辐射场, 逆渲染, 神经场, 表面重建, 材质光照估计

Abstract:

In computer vision and computer graphics, 3D reconstruction aims to generate high-fidelity digital models of real objects and scenes from 2D images, videos, or other sensor data, and has long attracted attention from both academia and industry. In recent years, deep learning has continuously improved reconstruction accuracy and efficiency, enabling applications such as relighting, digital twins, and virtual reality. With the advent of Neural Radiance Fields (NeRF), neural-field-based reconstruction has become increasingly mainstream; inverse rendering has been incorporated to enhance appearance disentanglement, forming a more complete reconstruction framework. Motivated by a rapidly growing yet fragmented literature, this survey focused on static objects and scenes and organized neural-field-based inverse-rendering 3D reconstruction into two components: neural-field surface reconstruction, and neural-field material and illumination estimation. For each component, core research questions were distilled and representative methods were summarized following a “research problem-technical solution” perspective. Their key principles and derivations were analyzed to inform future algorithm design. In addition, commonly used datasets and evaluation metrics for both directions were compiled, and their practical details and applicability were discussed. Finally, open challenges and promising future directions were outlined.

Key words: 3D reconstruction, neural radiance field, inverse rendering, neural fields, surface reconstruction, material illumination estimation

中图分类号:

TP391.41

周雪杨, 沈旭昆, 胡勇. 基于神经场逆渲染的三维重建研究综述[J]. 图学学报, 2026, 47(3): 449-471.

ZHOU Xueyang, SHEN Xukun, HU Yong. A review of research on 3D reconstruction based on neural field inverse rendering[J]. Journal of Graphics, 2026, 47(3): 449-471.

图/表 22

图1 基于逆渲染的三维重建流程示意图

Fig. 1 Schematic diagram of 3D reconstruction process based on inverse rendering

图2 基于神经场逆渲染的三维重建研究中的研究问题

Fig. 2 Research problems in 3D reconstruction based on neural field inverse rendering

图3 NeRF[6]算法流程

Fig. 3 The pipeline of NeRF[6]

图4 基于神经场的表面重建的“问题-技术方案”分类树

Fig. 4 Classification tree of “problem-technical solution” based on neural field for surface reconstruction

图5 神经隐式偏移场[22]意图

Fig. 5 Schematic diagram of implicit displacement fields[22]

图6 MonoSDF[30]流程示意图

Fig. 6 Schematic diagram of MonoSDF[30]

图7 Ref-NeRF[37]流程示意图

Fig. 7 Comparison diagram of Ref-NeRF[37]

图8 Ref-NeuS[46]流程示意图

Fig. 8 Schematic diagram of Ref-NeuS[46]

图9 TensoSDF[53]流程示意图

Fig. 9 Schematic diagram of TensoSDF[53]

图10 LTM[61]流程示意图

Fig. 10 Schematic diagram of LTM[61]

图11 MonoGSDF[73]流程示意图

Fig. 11 Schematic diagram of MonoGSDF[73]

图12 FourieRF[78]频率控制流程示意图

Fig. 12 Schematic diagram of frequency control process for FourieRF[78]

图13 NGLoD[80]流程示意图

Fig. 13 Schematic diagram of NGLoD[80]

图14 MFLOD[84]流程示意图

Fig. 14 Schematic diagram of MFLOD[84]

图15 基于神经场的材质光照估计的“问题-技术方案”分类树

Fig. 15 Classification tree of “problem-technical solution” based on neural field for material illumination estimation

图16 TensoIR[95]流程示意图

Fig. 16 Schematic diagram of TensoIR[95]

图17 InvRender[101]流程示意图

Fig. 17 Schematic diagram of InvRender[101]

图18 NDE[108]流程示意图

Fig. 18 Schematic diagram of NDE[108]

图19 TensoFlow[114]采样器示意图

Fig. 19 Schematic diagram of the sampler of TensoFlow[114]

图20 PIR[118]流程示意图

Fig. 20 Schematic diagram of PIR[118]

图21 VQ-NeRF[125]流程示意图

Fig. 21 Schematic diagram of VQ-NeRF[125]

图22 神经场调制流程示意图

Fig. 22 Schematic diagram of neural field conditioning

参考文献 145

[1]	SCHÖNBERGER J L, FRAHM J M. Structure-from-motion revisited[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2016: 4104-4113.
[2]	SEITZ S M, CURLESS B, DIEBEL J, et al. A comparison and evaluation of multi-view stereo reconstruction algorithms[C]// 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2006: 519-528.
[3]	PARK J J, FLORENCE P, STRAUB J, et al. DeepSDF: learning continuous signed distance functions for shape representation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2019: 165-174.
[4]	NIEMEYER M, MESCHEDE L, OECHSLE M, et al. Differentiable volumetric rendering: learning implicit 3D representations without 3D supervision[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2020: 3501-3512.
[5]	YARIV L, KASTEN Y, MORAN D, et al. Multiview neural surface reconstruction by disentangling geometry and appearance[C]//The 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 210.
[6]	MILDENHALL B, SRINIVASAN P P, TANCIK M, et al. NeRF: representing scenes as neural radiance fields for view synthesis[C]//The 16th European Conference on Computer Vision. Cham: Springer, 2020: 405-421.
[7]	XIE Y H, TAKIKAWA T, SAITO S, et al. Neural fields in visual computing and beyond[J]. Computer Graphics Forum, 2022, 41(2): 641-676. DOI URL
[8]	TEWARI A, THIES J, MILDENHALL B, et al. Advances in neural rendering[J]. Computer Graphics Forum, 2022, 41(2): 703-735. DOI URL
[9]	GAO K L, GAO Y N, HE H J, et al. NeRF: neural radiance field in 3D vision:a comprehensive review[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2210.00379.
[10]	RABBY A S A, ZHANG C C. BeyondPixels: a comprehensive review of the evolution of neural radiance fields[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2306.03000.
[11]	XIAO W H, CHIERCHIA R, CRUZ R S, et al. Neural radiance fields for the real world: a survey[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2501.13104.
[12]	杨主伦, 刘烨斌, 举雅琨, 等. 场景重光照研究综述[J]. 中国图象图形学报, 2025, 30(6): 1543-1575.
	YANG Z L, LIU Y B, JU Y K, et al. Review of scene relighting methods[J]. Journal of Image and Graphics, 2025, 30(6): 1543-1575(in Chinese). DOI URL
[13]	董相涛, 马鑫, 潘成伟, 等. 室外大场景神经辐射场综述[J]. 图学学报, 2024, 45(4): 631-649. DOI
	DONG X T, MA X, PAN C W, et al. A review of neural radiance fields for outdoor large scenes[J]. Journal of Graphics, 2024, 45(4): 631-649(in Chinese). DOI
[14]	王稚儒, 常远, 鲁鹏, 等. 神经辐射场加速算法综述[J]. 图学学报, 2024, 45(1): 1-13. DOI
	WANG Z R, CHANG Y, LU P, et al. A review on neural radiance fields acceleration[J]. Journal of Graphics, 2024, 45(1): 1-13(in Chinese). DOI
[15]	黄家晖, 穆太江. 动态三维场景重建研究综述[J]. 图学学报, 2024, 45(1): 14-25. DOI
	HUANG J H, MU T J. A survey of dynamic 3D scene reconstruction[J]. Journal of Graphics, 2024, 45(1): 14-25(in Chinese). DOI
[16]	KAJIYA J T, VON HERZEN B P. Ray tracing volume densities[J]. ACM SIGGRAPH Computer Graphics, 1984, 18(3): 165-174. DOI URL
[17]	KAJIYA J T. The rendering equation[C]//The 13th Annual Conference on Computer Graphics and Interactive Technique. New York: ACM, 1986: 143-150.
[18]	NIMIER-DAVID M, VICINI D, ZELTNER T, et al. Mitsuba 2: a retargetable forward and inverse renderer[J]. ACM Transactions on Graphics, 2019, 38(6): 203.
[19]	OECHSLE M, PENG S Y, GEIGER A. UniSurf: unifying neural implicit surfaces and radiance fields for multi-view reconstruction[C]//2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 5569-5579.
[20]	YARIV L, GU J T, KASTEN Y, et al. Volume rendering of neural implicit surfaces[C]//The 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 367.
[21]	WANG P, LIU L J, LIU Y, et al. NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction[C]// The 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 2081.
[22]	WANG Y F, RAHMANN L, SORKINE-HORNUNG O. Geometry-consistent neural shape representation with implicit displacement fields[EB/OL]. [2025-08-20]. https://openreview.net/forum?id=yhCp5RcZD7.
[23]	SITZMANN V, MARTEL J N P, BERGMAN A W, et al. Implicit neural representations with periodic activation functions[C]//The 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 626.
[24]	WANG Y, SKOROKHODOV I, WONKA P. HF-NeuS: improved surface reconstruction using high-frequency details[C]//The 36th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2022: 143.
[25]	KULHANEK J, SATTLER T. Tetra-NeRF: representing neural radiance fields using tetrahedra[C]2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 18412-18423.
[26]	THOMAS D, FRANCO J S, BOYER E. 3D shape modeling with adaptive centroidal Voronoi tesselation on signed distance field[EB/OL]. [2025-08-27]. https://inria.hal.science/hal-04902175v1/file/MIRU2024_VortSDF.pdf.
[27]	HUANG Z J, LIANG Z H, ZHANG H J, et al. Sur2F:a hybrid representation for high-quality and efficient surface reconstruction from multi-view images[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2401.03704.
[28]	FU Q C, XU Q S, ONG Y S, et al. Geo-NeuS: geometry-consistent neural implicit surfaces learning for multi-view reconstruction[C]//The 36th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2022: 246.
[29]	ZHANG J Y, YAO Y, LI S W, et al. Critical regularizations for neural surface reconstruction in the wild[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 6260-6269.
[30]	YU Z H, PENG S Y, NIEMEYER M, et al. MonoSDF: exploring monocular geometric cues for neural implicit surface reconstruction[C]//The 36th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2022: 1814.
[31]	WANG J P, WANG P, LONG X X, et al. NeuRIS: neural reconstruction of indoor scenes using normal priors[C]//The 17th European Conference on Computer Vision. Cham: Springer, 2022: 139-155.
[32]	WEN S Q, JIANG H Q, ZENG C, et al. Depth-NeuS: neural implicit surfaces learning for multi-view reconstruction based on depth information optimization[C]//The 20th International Conference on Advanced Intelligent Computing Technology and Applications. Cham: Springer, 2024: 47-58.
[33]	DARMON F, BASCLE B, DEVAUX J C, et al. Improving neural implicit surfaces geometry with patch warping[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 6250-6259.
[34]	CHEN D C, ZHANG P, FELDMANN I, et al. Recovering fine details for neural implicit surface reconstruction[C]//2023 IEEE/CVF Winter Conference on Applications of Computer Vision. New York: IEEE Press, 2023: 4319-4328.
[35]	REN X L, CAO C J, FU Y W, et al. Improving neural surface reconstruction with feature priors from multi-view images[C]//The 18th European Conference on Computer Vision. Cham: Springer, 2024: 445-463.
[36]	SU W J, ZHANG C, XU Q S, et al. PSDF: prior-driven neural implicit surface learning for multi-view reconstruction[J]. IEEE Transactions on Visualization and Computer Graphics, 2025, 31(9): 5229-5244. DOI URL
[37]	VERBIN D, HEDMAN P, MILDENHALL B, et al. Ref-NeRF: structured view-dependent appearance for neural radiance fields[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 5481-5490.
[38]	BARRON J T, MILDENHALL B, TANCIK M, et al. Mip-NeRF: a multiscale representation for anti-aliasing neural radiance fields[C]//2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 5835-5844.
[39]	LIU Y, WANG P, LIN C, et al. NeRO: neural geometry and BRDF reconstruction of reflective objects from multiview images[J]. ACM Transactions on Graphics, 2023, 42(4): 114.
[40]	KARIS B, GAMES E. Real shading in unreal engine 4[J]. Proc. Physically Based Shading Theory Practice, 2013, 4(3): 1.
[41]	JIANG Z J, XU T, KATO H. Rethinking directional parameterization in neural implicit surface reconstruction[C]// The 18th European Conference on Computer Vision. Cham: Springer, 2024: 127-142.
[42]	HAN K, XIANG W. Multiscale tensor decomposition and rendering equation encoding for view synthesis[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 4232-4241.
[43]	MA L, AGRAWAL V, TURKI H, et al. SpecNeRF: Gaussian directional encoding for specular reflections[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 21188-21198.
[44]	GUO Y C, KANG D, BAO L C, et al. NeRFReN: neural radiance fields with reflections[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 18388-18397.
[45]	WANG F J H, RAKOTOSAONA M J, NIEMEYER M, et al. UniSDF: unifying neural representations for high-fidelity 3D reconstruction of complex scenes with reflections[C]//The 38th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 103.
[46]	GE W H, HU T, ZHAO H Y, et al. Ref-NeuS: ambiguity-reduced neural implicit surface learning for multi-view reconstruction with reflection[C]//2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 4228-4237.
[47]	VERBIN D, SRINIVASAN P P, HEDMAN P, et al. NeRF-Casting: improved view-dependent appearance with consistent reflections[C]//SIGGRAPH Asia 2024 Conference Papers. New York: ACM, 2024: 15.
[48]	MÜLLER T, EVANS A, SCHIED C, et al. Instant neural graphics primitives with a multiresolution hash encoding[J]. ACM Transactions on Graphics, 2022, 41(4): 102.
[49]	LIU L J, GU J T, ZAW LIN K, et al. Neural sparse voxel fields[C]//The 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 1313.
[50]	KERBL B, KOPANAS G, LEIMKÜHLER T, et al. 3D Gaussian splatting for real-time radiance field rendering[J]. ACM Transactions on Graphics, 2023, 42(4): 139.
[51]	LI Z S, MÜLLER T, EVANS A, et al. Neuralangelo: high-fidelity neural surface reconstruction[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 8456-8465.
[52]	WANG Y M, HAN Q, HABERMANN M, et al. NeuS2: fast learning of neural implicit surfaces for multi-view reconstruction[C]//2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 3272-3283.
[53]	LI J, WANG L, ZHANG L, et al. TensoSDF: roughness-aware tensorial representation for robust geometry and material reconstruction[J]. ACM Transactions on Graphics, 2024, 43(4): 150.
[54]	CHEN A P, XU Z X, GEIGER A, et al. TensoRF: tensorial radiance fields[C]//The 17th European Conference on Computer Vision. Cham: Springer, 2022: 333-350.
[55]	WANG Y Q, SKOROKHODOV I, WONKA P. PET-NeuS: positional encoding tri-planes for neural surfaces[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 12598-12607.
[56]	CHAN E R, LIN C Z, CHAN M A, et al. Efficient geometry-aware 3D generative adversarial networks[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 16102-16112.
[57]	TOUSSAINT B, THOMAS D, FRANCO J S. ProbeSDF: light field probes for neural surface reconstruction[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2025: 11026-11035.
[58]	WU T, WANG J Q, PAN X G, et al. Voxurf: voxel-based efficient and accurate neural surface reconstruction[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2208.12697.
[59]	CAI B W, HUANG J C, JIA R F, et al. NeuDA: neural deformable anchor for high-fidelity implicit surface reconstruction[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 8476-8485.
[60]	YARIV L, HEDMAN P, REISER C, et al. BakedSDF: meshing neural SDFs for real-time view synthesis[C]//ACM SIGGRAPH 2023 Conference Proceedings. New York: ACM, 2023: 46.
[61]	CHOI J, SHAH R, LI Q B, et al. LTM: lightweight textured mesh extraction and refinement of large unbounded scenes for efficient storage and real-time rendering[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 5053-5063.
[62]	TANG J X, ZHOU H, CHEN X K, et al. Delicate textured mesh recovery from NeRF via adaptive surface refinement[C]// 2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 17693-17703.
[63]	MUNKBERG J, CHEN W Z, HASSELGREN J, et al. Extracting triangular 3D models, materials, and lighting from images[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 8270-8280.
[64]	GAO J N, CHEN Z, YAN Y C, et al. EvaSurf: efficient view-aware implicit textured surface reconstruction[J]. IEEE Transactions on Visualization and Computer Graphics, 2025, 31(9): 6307-6320. DOI URL
[65]	ROJAS S, ZARZAR J, PÉREZ J C, et al. Re-ReND: real-time rendering of NeRFs across devices[C]//2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 3609-3618.
[66]	CHEN H L, LI C, WANG Y S, et al. NeuSG:neural implicit surface reconstruction with 3D Gaussian splatting guidance[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2312.00846.
[67]	YU M L, LU T, XU L N, et al. GSDF: 3DGS meets SDF for improved neural rendering and reconstruction[C]//The 38th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 4115.
[68]	XIANG H D, LI X H, CHENG K, et al. GaussianRoom: improving 3D Gaussian splatting with SDF guidance and monocular cues for indoor scene reconstruction[C]//2025 IEEE International Conference on Robotics and Automation. New York: IEEE Press, 2025: 2686-2693.
[69]	XU B X, HU J B, LI J Z, et al. GSurf:3D reconstruction via signed distance fields with direct Gaussian supervision[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2411.15723.
[70]	ZHANG W Y, LIU Y S, HAN Z H. Neural signed distance function inference through splatting 3D Gaussians pulled on zero-level set[C]//The 38th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 3231.
[71]	GAO Z H, BIAN J W, LIN G S, et al. SurfaceSplat: connecting surface reconstruction and Gaussian splatting[C]//IEEE International Conference on Computer Vision. New York: IEEE Press, 2025: 28525-28534.
[72]	LYU X Y, SUN Y T, HUANG Y H, et al. 3DGSR: implicit surface reconstruction with 3D Gaussian splatting[J]. ACM Transactions on Graphics, 2024, 43(6): 198.
[73]	LI K Y, NIEMEYER M, CHEN Z Y, et al. MonoGSDF: exploring monocular geometric cues for Gaussian splatting-guided implicit surface reconstruction[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2411.16898.
[74]	YE S, HE Y Z, LIN M, et al. PVP-Recon: progressive view planning via warping consistency for sparse-view surface reconstruction[J]. ACM Transactions on Graphics, 2024, 43(6): 191.
[75]	LONG X X, LIN C, WANG P, et al. SparseNeuS: fast generalizable neural surface reconstruction from sparse views[C]//The 17th European Conference on Computer Vision. Cham: Springer, 2022: 210-227.
[76]	REN Y F, WANG F J H, ZHANG T, et al. VolReCon: volume rendering of signed ray distance functions for generalizable multi-view reconstruction[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 16685-16695.
[77]	YANG J W, PAVONE M, WANG Y. FreeNeRF: improving few-shot neural rendering with free frequency regularization[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 8254-8263.
[78]	GOMEZ D, GONG B C, OVSJANIKOV M. FourieRF: few-shot NeRFs via progressive Fourier frequency control[C]//2025 International Conference on 3D Vision. New York: IEEE Press, 2025: 607-615.
[79]	XIE S X, ZHOU S Y, SAKURADA K, et al. G²fR: frequency regularization in grid-based feature encoding neural radiance fields[C]//The 18th European Conference on Computer Vision. Cham: Springer, 2024: 186-203.
[80]	TAKIKAWA T, LITALIEN J, YIN K X, et al. Neural geometric level of detail: real-time rendering with implicit 3D shapes[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2021: 11353-11362.
[81]	LIANG J B, ZHANG L Q, ZHAO Z R, et al. InfNeRF: towards infinite scale NeRF rendering with O(log n) space complexity[C]//SIGGRAPH Asia 2024 Conference Papers. New York: ACM, 2024: 1.
[82]	PETIT D, BOURGEOIS S, PAVEL D, et al. RING-NeRF: rethinking inductive biases for versatile and efficient neural fields[C]//The 18th European Conference on Computer Vision. Cham: Springer, 2024: 148-164.
[83]	LINDELL D B, VAN VEEN D, PARK J J, et al. BACON: band-limited coordinate networks for multiscale scene representation[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 16231-16241.
[84]	DOU Y S, ZHENG Z, JIN Q Q, et al. Multiplicative Fourier level of detail[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 1808-1817.
[85]	WU Z J, JIN Y H, YI K M. Neural Fourier filter bank[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 14153-14163.
[86]	LANDGRAF Z, HORNUNG A S, CABRAL R S. PINS: progressive implicit networks for multi-scale neural representations[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2202.04713.
[87]	SHABANOV A A, GOVINDARAJAN S, READING C, et al. BANF: band-limited neural fields for levels of detail reconstruction[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 20571-20580.
[88]	BI S, XU Z X, SUNKAVALLI K, et al. Deep reflectance volumes: relightable reconstructions from multi-view photometric images[C]//The 16th European Conference on Computer Vision. Cham: Springer, 2020: 294-311.
[89]	BI S, XU Z X, SRINIVASAN P P, et al. Neural reflectance fields for appearance acquisition[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2008.03824.
[90]	WALTER B, MARSCHNER S R, LI H S, et al. Microfacet models for refraction through rough surfaces[C]//The 18th Eurographics conference on Rendering Techniques. Goslar: Eurographics Association, 2007: 195-206.
[91]	ZHANG K, LUAN F J, WANG Q Q, et al. PhySG: inverse rendering with spherical Gaussians for physics-based material editing and relighting[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2021: 5449-5458.
[92]	BURLEY B. Physically-based shading at Disney[C]ACM SIGGRAPH Course Notes. New York: ACM, 2012: 1-7.
[93]	ZHANG K, LUAN F J, LI Z Q, et al. IRON: inverse rendering by optimizing neural SDFs and materials from photometric images[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 5555-5564.
[94]	ZHANG X M, SRINIVASAN P P, DENG B Y, et al. NeRFactor: neural factorization of shape and reflectance under an unknown illumination[J]. ACM Transactions on Graphics, 2021, 40(6): 237.
[95]	JIN H A, LIU I, XU P J, et al. TensoIR: tensorial inverse rendering[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 165-174.
[96]	WANG Z A, SHEN T C, GAO J, et al. Neural fields meet explicit geometric representations for inverse rendering of urban scenes[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 8370-8380.
[97]	ZARZAR J, GHANEM B. SplitNeRF: split sum approximation neural field for joint geometry, illumination, and material estimation[C]//The 38th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 222.
[98]	TORRANCE K E, SPARROW E M. Theory for off-specular reflection from roughened surfaces[J]. Journal of the Optical Society of America, 1967, 57(9): 1105-1114. DOI URL
[99]	ZHANG D H, WANG J Y, WANG S F, et al. RISE-SDF: a relightable information-shared signed distance field for glossy object inverse rendering[C]//2025 International Conference on 3D Vision. New York: IEEE Press, 2025: 597-606.
[100]	SRINIVASAN P P, DENG B Y, ZHANG X M, et al. NeRV: neural reflectance and visibility fields for relighting and view synthesis[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2021: 7491-7500.
[101]	ZHANG Y Q, SUN J M, HE X Y, et al. Modeling indirect illumination for inverse rendering[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 18622-18631.
[102]	ZENG C, CHEN G J, DONG Y, et al. Relighting neural radiance fields with shadow and highlight hints[C]//ACM SIGGRAPH 2023 Conference Proceedings. New York: ACM, 2023: 73.
[103]	WANG H Y, HU W B, ZHU L, et al. Inverse rendering of glossy objects via the neural plenoptic function and radiance fields[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 19999-20008.
[104]	YANG Z Y, CHEN Y Z, GAO X Y, et al. SIRE-IR: inverse rendering for BRDF reconstruction with shadow and illumination removal in high-illuminance scenes[EB/OL]. [2025-03-10]. https://arxiv.org/abs/2310.13030.
[105]	WU H Q, HU Z P, LI L C, et al. NeFII: inverse rendering for reflectance decomposition with near-field indirect illumination[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 4295-4304.
[106]	YAO Y, ZHANG J Y, LIU J B, et al. NeILF: neural incident light field for physically-based material estimation[C]//The 17th European Conference on Computer Vision. Cham: Springer, 2022: 700-716.
[107]	ZHANG J Y, YAO Y, LI S W, et al. NeILF++: inter-reflectable light fields for geometry and material estimation[C]//2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 3578-3587.
[108]	WU L W, BI S, XU Z X, et al. Neural directional encoding for efficient and accurate view-dependent appearance modeling[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 21157-21166.
[109]	FEI F, TANG J J, TAN P, et al. VMINer: versatile multi-view inverse rendering with near-and far-field light sources[C]// 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 11800-11809.
[110]	LING J W, YU R H, XU F, et al. NeRF as a non-distant environment emitter in physics-based inverse rendering[C]// ACM SIGGRAPH 2024 Conference Papers. New York: ACM, 2024: 39.
[111]	JEONG J, KOO J, ZHANG Q M, et al. ESR-NeRF: emissive source reconstruction using LDR multi-view images[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 4598-4609.
[112]	CHEN Z Y, DING C J, GUO J F, et al. L-tracing: fast light visibility estimation on neural surfaces by sphere tracing[C]//The 17th European Conference on Computer Vision. Cham: Springer, 2022: 217-233.
[113]	SUN C, CAI G Y, LI Z Q, et al. Neural-PBIR reconstruction of shape, material, and illumination[C]//2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 18000-18010.
[114]	GU C, WEI X F, ZHANG L, et al. TensoFlow: tensorial flow-based sampler for inverse rendering[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2025: 495-504.
[115]	DAI Y X, WANG Q, ZHU J S, et al. MIRReS: multi-bounce inverse rendering using reservoir sampling[EB/OL]. [2025-03-10]. https://arxiv.org/html/2406.16360v1.
[116]	CHENG Z A, LI J X, LI H D. WildLight: in-the-wild inverse rendering with a flashlight[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 4305-4314.
[117]	MAO S, WU C M, SHEN Z L, et al. NeuS-PIR: learning relightable neural surface using pre-integrated rendering[J]. Computational Visual Media, 2025, 11(4): 727-744. DOI URL
[118]	BAO J Z, CHEN G Y, CUI S G. PIR: photometric inverse rendering with shading cues modeling and surface reflectance regularization[C]//2025 International Conference on 3D Vision. New York: IEEE Press, 2025: 544-555.
[119]	WU S A, BASU S, BRÖDERMANN T, et al. PBR-NeRF: inverse rendering with physics-based neural fields[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2025: 10974-10984.
[120]	ZHONG L C, YANG L X, LI K L, et al. Color-NeuS: reconstructing neural implicit surfaces with color[C]// International Conference on 3D Vision. New York: IEEE Press, 2024: 631-640.
[121]	ZHANG J Y, YANG G S, TULSIANI S, et al. NeRS: neural reflectance surfaces for sparse-view 3D reconstruction in the wild[C]//The 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 2283.
[122]	XIANG F B, XU Z X, HAŠAN M, et al. NeuTex: neural texture mapping for volumetric neural rendering[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2021: 7115-7124.
[123]	WU T, SUN J M, LAI Y K, et al. De-NeRF: decoupled neural radiance fields for view-consistent appearance editing and high-frequency environmental relighting[C]//ACM SIGGRAPH 2023 Conference Proceedings. New York: ACM, 2023: 74.
[124]	LIANG R F, CHEN H T, LI C L, et al. ENVIDR: implicit differentiable renderer with neural environment lighting[C]// 2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 79-89.
[125]	ZHONG H L, ZHANG J B, LIAO J. VQ-NeRF: neural reflectance decomposition and editing with vector quantization[J]. IEEE Transactions on Visualization and Computer Graphics, 2024, 30(9): 6247-6260. DOI URL
[126]	MARTIN-BRUALLA R, RADWAN N, SAJJADI M S M, et al. NeRF in the wild: neural radiance fields for unconstrained photo collections[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2021: 7206-7215.
[127]	BOSS M, BRAUN R, JAMPANI V, et al. NeRD: neural reflectance decomposition from image collections[C]//2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 12664-12674.
[128]	BOSS M, JAMPANI V, BRAUN R, et al. Neural-PIL: neural pre-integrated lighting for reflectance decomposition[C]//The 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 818.
[129]	KUANG Z F, OLSZEWSKI K, CHAI M L, et al. NeROIC: neural rendering of objects from online image collections[J]. ACM Transactions on Graphics, 2022, 41(4): 56.
[130]	ENGELHARDT A, RAJ A, BOSS M, et al. SHINOBI: shape and illumination using neural object decomposition via BRDF optimization in-the-wild[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2024: 19636-19646.
[131]	JENSEN R, DAHL A, VOGIATZIS G, et al. Large scale multi-view stereopsis evaluation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2014: 406-413.
[132]	YAO Y, LUO Z X, LI S W, et al. BlendedMVS: a large-scale dataset for generalized multi-view stereo networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2020: 1787-1796.
[133]	STRECHA C, VON HANSEN W, VAN GOOL L, et al. On benchmarking camera calibration and multi-view stereo for high resolution imagery[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2008: 1-8.
[134]	KNAPITSCH A, PARK J, ZHOU Q Y, et al. Tanks and temples: benchmarking large-scale scene reconstruction[J]. ACM Transactions on Graphics, 2017, 36(4): 78.
[135]	VOYNOV O, BOBROVSKIKH G, KARPYSHEV P, et al. Multi-sensor large-scale dataset for multi-view 3D reconstruction[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 21392-21403.
[136]	KUANG Z F, ZHANG Y Z, YU H X, et al. Stanford-ORB: a real-world 3D object inverse rendering benchmark[C]//The 37th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2023: 2033.
[137]	DONG Z, CHEN K, LV Z Y, et al. Digital twin catalog: a large-scale photorealistic 3D object digital twin dataset[C]// 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2025: 753-763.
[138]	LIU I, CHEN L H, FU Z Y, et al. OpenIllumination: a multi-illumination dataset for inverse rendering evaluation on real objects[C]//The 37th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2023: 1607.
[139]	UMMENHOFER B, AGRAWAL S, SEPULVEDA R, et al. Objects with lighting: a real-world dataset for evaluating reconstruction and rendering for object relighting[C]// International Conference on 3D Vision. New York: IEEE Press, 2024: 137-147.
[140]	DAI A, CHANG A X, SAVVA M, et al. ScanNet: richly-annotated 3D reconstructions of indoor scenes[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2017: 2432-2443.
[141]	STRAUB J, WHELAN T, MA L N, et al. The Replica dataset: a digital replica of indoor spaces[EB/OL]. [2025-03-10]. https://arxiv.org/abs/1906.05797.
[142]	MAGGIORI E, TARABALKA Y, CHARPIAT G, et al. Can semantic labeling methods generalize to any city? the INRIA aerial image labeling benchmark[C]//2017 IEEE International Geoscience and Remote Sensing Symposium. New York: IEEE Press, 2017: 3226-3229.
[143]	WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. DOI PMID
[144]	ZHANG R, ISOLA P, EFROS A A, et al. The unreasonable effectiveness of deep features as a perceptual metric[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2018: 586-595.
[145]	HEUSEL M, RAMSAUER H, UNTERTHINER T, et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium[C]//The 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6629-6640.

基于神经场逆渲染的三维重建研究综述

A review of research on 3D reconstruction based on neural field inverse rendering

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 22

参考文献 145

相关文章 15

编辑推荐

Metrics

本文评价

[1]	徐晓峰, 徐延宁, 王璐. 控制变量技术在渲染领域中的应用综述[J]. 图学学报, 2026, 47(3): 472-491.
[2]	廖健康, 张严辞. 针对过度重建问题的频率强度高斯泼溅算法[J]. 图学学报, 2026, 47(3): 564-575.
[3]	任皓, 李少波, 弓茂, 王博. 基于特征点引导干扰物识别的神经辐射场重建[J]. 图学学报, 2026, 47(1): 111-119.
[4]	潘宇轩, 金锐, 刘雨, 张琳. 基于生成模型的无监督多视点立体视觉网络[J]. 图学学报, 2026, 47(1): 29-38.
[5]	黄敬, 时瑞浩, 宋文明, 郭和攀, 魏璜, 魏小松, 姚剑. 自动驾驶图像合成方法综述：从模拟器到新范式[J]. 图学学报, 2025, 46(5): 931-949.
[6]	郭铭策, 黄琲, 程乐超, 王章野. 联合点云先验的神经隐式表面重建加速方法[J]. 图学学报, 2025, 46(4): 807-817.
[7]	王道累, 丁子健, 杨君, 郑劭恺, 朱瑞, 赵文彬. 基于体素网格特征的NeRF大场景重建方法[J]. 图学学报, 2025, 46(3): 502-509.
[8]	黄志勇, 佘雅丽, 华喜锋, 向梦丽, 杨晨龙, 丁妥君. DCSplat：一种深度约束的稀疏视角三维重建方法[J]. 图学学报, 2025, 46(3): 510-519.
[9]	周峥, 戴亚桥, 易任娇, 蓝龙, 朱晨阳. 基于RGB特征的下一个最优视图导航技术[J]. 图学学报, 2025, 46(3): 551-557.
[10]	胡悦, 孙智达, 黄惠. 面向无人机路径规划的可视分析系统[J]. 图学学报, 2025, 46(3): 655-665.
[11]	孙禾衣, 李艺潇, 田希, 张松海. 结合程序内容生成与扩散模型的图像到三维瓷瓶生成技术[J]. 图学学报, 2025, 46(2): 332-344.
[12]	周伟, 苍慜楠, 程浩宗. 基于AR技术的文物数字化三维图像重建方法[J]. 图学学报, 2025, 46(2): 369-381.
[13]	邱佳新, 宋倩云, 徐丹. 基于改进神经辐射场的民族舞蹈重建方法[J]. 图学学报, 2025, 46(2): 415-424.
[14]	谢文想, 许威威. 辐射场表面物点引导的主动视图选择[J]. 图学学报, 2025, 46(1): 179-187.
[15]	熊超, 王云艳, 罗雨浩. 特征对齐与上下文引导的多视图三维重建[J]. 图学学报, 2024, 45(5): 1008-1016.