Jiawei Zhang, Lei Huang, Lin Gu, Jiahe Li, Xiao Bai, Jin Zheng, Xiaohan Yu
We lifted 12 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| jiaw-z/CoR-GS | canonical | 4 of 12 |
| Function | Status | Where it lives |
|---|---|---|
| l1_loss | Ran | jiaw-z/CoR-GS/utils/loss_utils.py pointer only (licence: NONE) · get_code("ac0e42d6fbcfbbe6") |
| l2_loss | Ran | jiaw-z/CoR-GS/utils/loss_utils.py pointer only (licence: NONE) · get_code("8c3b0f873ba11813") |
| normalize_activation | Ran | jiaw-z/CoR-GS/lpipsPyTorch/modules/utils.py pointer only (licence: NONE) · get_code("1dab900b2adbe38e") |
| read_next_bytes | Ran | jiaw-z/CoR-GS/scene/colmap_loader.py pointer only (licence: NONE) · get_code("56858e04e6fdb2ff") |
| custom_sort | Not yet run | jiaw-z/CoR-GS/metrics_dtu.py pointer only (licence: NONE) · get_code("f8a568a9009f4ade") |
| get_network | Not yet run | jiaw-z/CoR-GS/lpipsPyTorch/modules/networks.py pointer only (licence: NONE) · get_code("07bd0da29c4dc7bb") |
| get_state_dict | Not yet run | jiaw-z/CoR-GS/lpipsPyTorch/modules/utils.py pointer only (licence: NONE) · get_code("b06f27c08cf5d0ca") |
| l1_loss_mask | Not yet run | jiaw-z/CoR-GS/utils/loss_utils.py pointer only (licence: NONE) · get_code("70d775a44a693dae") |
| qvec2rotmat | Not yet run | jiaw-z/CoR-GS/scene/colmap_loader.py pointer only (licence: NONE) · get_code("6ce64cf0fbcd6bb1") |
| readImages | Not yet run | jiaw-z/CoR-GS/metrics.py pointer only (licence: NONE) · get_code("2a05973a17f517e6") |
| readImages | Not yet run | jiaw-z/CoR-GS/metrics_dtu.py pointer only (licence: NONE) · get_code("f0a7e7830ac7d9d7") |
| rotmat2qvec | Not yet run | jiaw-z/CoR-GS/scene/colmap_loader.py pointer only (licence: NONE) · get_code("659bc4e7e63ed8f9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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: (i) Co-pruning considers Gaussians that exhibit high point disagreement in inaccurate positions and prunes them. (ii) 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.12110")
get_code_for_paper("2405.12110")
have("2405.12110")
Connect an agent — have() is free.