Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization

About

3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduces a new co-regularization perspective for improving sparse-view 3DGS. When training two 3D Gaussian radiance fields, we observe that the two radiance fields exhibit point disagreement and rendering disagreement that can unsupervisedly predict reconstruction quality, stemming from the randomness of densification implementation. We further quantify the two disagreements and demonstrate the negative correlation between them and accurate reconstruction, which allows us to identify inaccurate reconstruction without accessing ground-truth information. Based on the study, we propose CoR-GS, which identifies and suppresses inaccurate reconstruction based on the two disagreements: (1) Co-pruning considers Gaussians that exhibit high point disagreement in inaccurate positions and prunes them. (2) Pseudo-view co-regularization considers pixels that exhibit high rendering disagreement are inaccurate and suppress the disagreement. Results on LLFF, Mip-NeRF360, DTU, and Blender demonstrate that CoR-GS effectively regularizes the scene geometry, reconstructs the compact representations, and achieves state-of-the-art novel view synthesis quality under sparse training views.

Jiawei Zhang, Jiahe Li, Xiaohan Yu, Lei Huang, Lin Gu, Jin Zheng, Xiao Bai• 2024

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisLLFF 3-view
PSNR20.473
95
Novel View SynthesisLLFF 9-view
PSNR26.475
75
Novel View SynthesisLLFF 6-view
PSNR24.777
74
Novel View SynthesisDTU 3-view
PSNR19.21
47
Novel View SynthesisReplica
PSNR20.066
39
Novel View SynthesisBlender Synthetic 8-view (test)
PSNR24.43
36
Novel View SynthesisMip-NeRF 360 12-view
PSNR19.52
32
Novel View SynthesisMip-NeRF 360 24-view
PSNR23.55
19
Semantic segmentationScanNet (novel views)
mIoU34.17
15
Novel View SynthesisScanNet (novel view)
PSNR21.801
15
Showing 10 of 15 rows

Other info

Follow for update