Implicit surface animation rendering based on temporal interval inversion

doi:10.11996/JG.j.2095-302X.2025030635

Abstract

Abstract:

Animation rendering is an important branch of computer graphics that focuses on generating temporal dynamic image sequences. The common animation rendering methods involves per-frame rendering of geometric scenes along the timeline, which can easily lead to the waste of computing resources. To enhance the animation rendering efficiency, an implicit surface animation rendering method based on temporal interval reversal was proposed. This method exploited a sparse octree mesh to divide the implicit scene space, employed interval arithmetic for recursive subdivision of the implicit scene, and categorized the scenes containing implicit surfaces into interior, exterior, and surface areas. Interval arithmetic was utilized to limit the range of the time derivative, thereby localizing changes within the implicit scene. There were intervals of relative or absolute stillness between multiple consecutive implicit surfaces, and by selectively re-evaluating areas while maintaining the global error, the occlusion between implicit surfaces was achieved. Finally, parallelized threads were utilized to render implicit surface animation. Experimental results showed that the proposed method, compared with the frame-by-frame rendering method, achieved an acceleration of several tens of times while maintaining the rendering quality.

Key words: implicit surface, octree algorithm, recursive subdivision, interval arithmetic, implicit surface occlusion

CLC Number:

TP391

LI Xiaoli, ZHANG Kun, DU Zhenlong, CHEN Dong, SONG Shuang. Implicit surface animation rendering based on temporal interval inversion[J]. Journal of Graphics, 2025, 46(3): 635-641.

Figures/Tables 9

References 24

[1]	SCHOTT H, PARIS A, FOURNIER L, et al. Large-scale terrain authoring through interactive erosion simulation[J]. ACM Transactions on Graphics, 2023, 42(5): 162.
[2]	CORDONNIER G, JOUVET G, PEYTAVIE A, et al. Forming terrains by glacial erosion[J]. ACM Transactions on Graphics, 2023, 42(4): 61.
[3]	SMITH H J, ZHENG Q Y, LI Y F, et al. A method for animating children’s drawings of the human figure[J]. ACM Transactions on Graphics, 2023, 42(3): 32.
[4]	TANG X J, WANG H, HU B, et al. Real-time controllable motion transition for characters[J]. ACM Transactions on Graphics, 2022, 41(4): 137.
[5]	ALLIEZ P, COHEN-STEINER D, DEVILLERS O, et al. Anisotropic polygonal remeshing[J]. ACM Transactions on Graphics, 2003, 22(3): 485-493.
[6]	李佳琦, 王辉, 郭宇. 基于Transformer的三角形网格分类分割网络[J]. 图学学报, 2024, 45(1): 78-89. DOI
	LI J Q, WANG H, GUO Y. Classification and segmentation network based on Transformer for triangular mesh[J]. Journal of Graphics, 2024, 45(1): 78-89 (in Chinese). DOI
[7]	VERHOEVEN F, VAXMAN A, VAXMAN T, et al. Dev2PQ: planar quadrilateral strip remeshing of developable surfaces[J]. ACM Transactions on Graphics, 2022, 41(3): 29.
[8]	ZHAO C H, WANG W X, YAN Y M, et al. A novel object-level building-matching method across 2D images and 3D point clouds based on the signed distance descriptor (SDD)[J]. Remote Sensing, 2023, 15(12): 2974.
[9]	ZHAO Y, ZHANG J H, WANG Y H, et al. KD-Box: line-segment-based KD-tree for interactive exploration of large-scale time-series data[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 28(1): 890-900.
[10]	杨兴强, 张彩明, 刘毅. 体数据中边界点计算的新方法[J]. 计算机研究与发展, 2007, 44(7): 1114-1120.
	YANG X Q, ZHANG C M, LIU Y. A new method to find the boundary point from volume data[J]. Journal of Computer Research and Development, 2007, 44(7): 1114-1120 (in Chinese).
[11]	KEETER M J. Massively parallel rendering of complex closed-form implicit surfaces[J]. ACM Transactions on Graphics, 2020, 39(4): 141.
[12]	DU X Y, ZHOU Q N, CARR N, et al. Robust computation of implicit surface networks for piecewise linear functions[J]. ACM Transactions on Graphics, 2022, 41(4): 41.
[13]	KOMARICHEV A, HUA J, ZHONG Z C. DiffSVR: differentiable neural implicit surface rendering for single-view reconstruction with highly sparse depth prior[J]. Computer-Aided Design, 2023, 164: 103604.
[14]	REN J Y, FUJITA Y, NAKATA S. Interactive restoration of three-dimensional implicit surface with irregular parts[J]. CMES - Computer Modeling in Engineering and Sciences, 2023, 136(3): 2111-2125.
[15]	张肇轩, 王诚斌, 杨鑫, 等. 基于模板替换的室内场景建模方法研究[J]. 图学学报, 2020, 41(2): 270-276. DOI
	ZHANG Z X, WANG C B, YANG X, et al. Indoor scene modeling method based on template replacement[J]. Journal of Graphics, 2020, 41(2): 270-276 (in Chinese).
[16]	ZIENIUK E, KAPTURCZAK M. Interval arithmetic in modeling and solving Laplace’s equation problems with uncertainly defined boundary shape[J]. Engineering Analysis with Boundary Elements, 2021, 125: 110-123.
[17]	CONTRERAS I, CALM R, SAINZ M A, et al. Combining grammatical evolution with modal interval analysis: an application to solve problems with uncertainty[J]. Mathematics, 2021, 9(6): 631.
[18]	ZHAO M Y, YAN W J, YUEN K V, et al. Non-probabilistic uncertainty quantification for dynamic characterization functions using complex ratio interval arithmetic operation of multidimensional parallelepiped model[J]. Mechanical Systems and Signal Processing, 2021, 156: 107559.
[19]	XIONG R C, LU Y, CHEN C, et al. ETER: elastic tessellation for real-time pixel-accurate rendering of large-scale NURBS models[J]. ACM Transactions on Graphics, 2023, 42(4): 133.
[20]	YANG L, DENG L, MOHAMMAD H H, et al. An optimal algorithm for online non-convex learning[J]. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2018, 2(2): 25.
[21]	ALACAOGLU A, BÖHM A, MALITSKY Y. Beyond the golden ratio for variational inequality algorithms[J]. The Journal of Machine Learning Research, 2024, 24(1): 172.
[22]	GEOFFREY C, GUILLAUME L, MATTHIEU L. Robust high dimensional learning for Lipschitz and convex losses[J]. The Journal of Machine Learning Research, 2020, 21(1): 233.
[23]	HAYDEL J, YUKSEL C, SEILER L. Locally-adaptive level-of-detail for hardware-accelerated ray tracing[J]. ACM Transactions on Graphics, 2023, 42(6): 196.
[24]	WEI Y X, CHEN J, BURRIDGE R, et al. Hadamard integrator for time-dependent wave equations: Lagrangian formulation via ray tracing[J]. Journal of Computational Physics, 2024, 497: 112637.

场景	ε	δ	平均帧时间/ms	总加速	平均帧加速
融球建筑	1024³	0.01	66.17	19.71	71.95
		0.03	31.47	41.44	126.01
		0.06	19.56	66.68	193.99
	256³	0.01	7.03	12.19	16.02
		0.03	4.70	18.25	22.16
		0.06	3.58	23.92	28.33
扭曲线圈	1024³	0.01	224.82	3.05	3.10
		0.03	120.34	5.70	5.92
		0.06	55.02	17.48	13.38
	256³	0.01	12.06	3.14	3.16
		0.03	10.73	3.52	3.55
		0.06	8.28	4.57	4.63
摆动小球	1024³	0.01	35.76	6.09	6.66
		0.03	26.86	8.11	9.19
		0.06	21.67	10.05	11.63
	256³	0.01	5.64	3.61	3.72
		0.03	4.99	4.09	4.20
		0.06	4.66	4.38	4.51
滑动琴块	1024³	0.01	18.86	28.68	87.84
		0.03	17.08	31.67	92.37
		0.06	14.05	38.50	98.42
	256³	0.01	2.92	13.48	14.86
		0.03	2.96	13.29	14.59
		0.06	2.90	13.54	14.94

场景	ε	δ	平均帧时间/ms	总加速	平均帧加速
融球建筑	1024³	0.01	66.17	19.71	71.95
		0.03	31.47	41.44	126.01
		0.06	19.56	66.68	193.99
	256³	0.01	7.03	12.19	16.02
		0.03	4.70	18.25	22.16
		0.06	3.58	23.92	28.33
扭曲线圈	1024³	0.01	224.82	3.05	3.10
		0.03	120.34	5.70	5.92
		0.06	55.02	17.48	13.38
	256³	0.01	12.06	3.14	3.16
		0.03	10.73	3.52	3.55
		0.06	8.28	4.57	4.63
摆动小球	1024³	0.01	35.76	6.09	6.66
		0.03	26.86	8.11	9.19
		0.06	21.67	10.05	11.63
	256³	0.01	5.64	3.61	3.72
		0.03	4.99	4.09	4.20
		0.06	4.66	4.38	4.51
滑动琴块	1024³	0.01	18.86	28.68	87.84
		0.03	17.08	31.67	92.37
		0.06	14.05	38.50	98.42
	256³	0.01	2.92	13.48	14.86
		0.03	2.96	13.29	14.59
		0.06	2.90	13.54	14.94

场景	方法	平均帧时间/ms	总加速	平均帧加速
融球建筑	Per-frame	1304.05	1.00	1.00
融球建筑	Ours	19.56	66.68	193.99
扭曲线圈	Per-frame	686.04	1.00	1.00
扭曲线圈	Ours	55.02	17.48	13.38
摆动小球	Per-frame	217.85	1.00	1.00
摆动小球	Ours	21.67	10.05	11.63
滑动琴块	Per-frame	540.87	11.00	1.00
滑动琴块	Ours	14.05	38.50	98.42

场景	方法	平均帧时间/ms	总加速	平均帧加速
融球建筑	Per-frame	1304.05	1.00	1.00
融球建筑	Ours	19.56	66.68	193.99
扭曲线圈	Per-frame	686.04	1.00	1.00
扭曲线圈	Ours	55.02	17.48	13.38
摆动小球	Per-frame	217.85	1.00	1.00
摆动小球	Ours	21.67	10.05	11.63
滑动琴块	Per-frame	540.87	11.00	1.00
滑动琴块	Ours	14.05	38.50	98.42