We lifted 11 functions out of this paper's own repositories and ran 6 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 |
|---|---|---|
| ustc-imcl/rdo-gaussian | canonical | 6 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| gaussian | Ran | ustc-imcl/rdo-gaussian/utils/loss_utils.py pointer only (licence: NONE) · get_code("c56b7ef16f309a45") |
| l1_loss | Ran | ustc-imcl/rdo-gaussian/utils/loss_utils.py pointer only (licence: NONE) · get_code("ac0e42d6fbcfbbe6") |
| l2_loss | Ran | ustc-imcl/rdo-gaussian/utils/loss_utils.py pointer only (licence: NONE) · get_code("8c3b0f873ba11813") |
| normalize_activation | Ran | ustc-imcl/rdo-gaussian/lpipsPyTorch/modules/utils.py pointer only (licence: NONE) · get_code("1dab900b2adbe38e") |
| readImages | Ran | ustc-imcl/rdo-gaussian/metrics.py pointer only (licence: NONE) · get_code("cdd00787894554b5") |
| read_next_bytes | Ran | ustc-imcl/rdo-gaussian/scene/colmap_loader.py pointer only (licence: NONE) · get_code("56858e04e6fdb2ff") |
| get_network | Not yet run | ustc-imcl/rdo-gaussian/lpipsPyTorch/modules/networks.py pointer only (licence: NONE) · get_code("07bd0da29c4dc7bb") |
| get_state_dict | Not yet run | ustc-imcl/rdo-gaussian/lpipsPyTorch/modules/utils.py pointer only (licence: NONE) · get_code("b06f27c08cf5d0ca") |
| pmf_to_quantized_cdf | Not yet run | ustc-imcl/rdo-gaussian/utils/entropy_model.py pointer only (licence: NONE) · get_code("b5dd898abb1e9dd4") |
| qvec2rotmat | Not yet run | ustc-imcl/rdo-gaussian/scene/colmap_loader.py pointer only (licence: NONE) · get_code("6ce64cf0fbcd6bb1") |
| rotmat2qvec | Not yet run | ustc-imcl/rdo-gaussian/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) has become an emerging technique with remarkable potential in 3D representation and image rendering. However, the substantial storage overhead of 3DGS significantly impedes its practical applications. In this work, we formulate the compact 3D Gaussian learning as an end-to-end Rate-Distortion Optimization (RDO) problem and propose RDO-Gaussian that can achieve flexible and continuous rate control. RDO-Gaussian addresses two main issues that exist in current schemes: 1) Different from prior endeavors that minimize the rate under the fixed distortion, we introduce dynamic pruning and entropy-constrained vector quantization (ECVQ) that optimize the rate and distortion at the same time. 2) Previous works treat the colors of each Gaussian equally, while we model the colors of different regions and materials with learnable numbers of parameters. We verify our method on both real and synthetic scenes, showcasing that RDO-Gaussian greatly reduces the size of 3D Gaussian over 40x, and surpasses existing methods in rate-distortion performance.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.01597")
get_code_for_paper("2406.01597")
have("2406.01597")
Connect an agent — have() is free.