We lifted 5 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| ActiveVisionLab/nope-nerf | canonical | 5 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| arange_pixels | Ran | ActiveVisionLab/nope-nerf/model/common.py code served (permissive licence) · get_code("1cfdd8b5660fd081") |
| encode_position | Ran | ActiveVisionLab/nope-nerf/model/official_nerf.py code served (permissive licence) · get_code("74072d2f0e501339") |
| get_mask | Ran | ActiveVisionLab/nope-nerf/model/common.py code served (permissive licence) · get_code("0a96d4d9cdb21375") |
| is_url | Ran | ActiveVisionLab/nope-nerf/model/checkpoints.py code served (permissive licence) · get_code("71dbed7bd8b18214") |
| to_pytorch | Ran | ActiveVisionLab/nope-nerf/model/common.py code served (permissive licence) · get_code("cc20eeee3ba3cb0d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Training a Neural Radiance Field (NeRF) without pre-computed camera poses is challenging. Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes. However, these methods still face difficulties during dramatic camera movement. We tackle this challenging problem by incorporating undistorted monocular depth priors. These priors are generated by correcting scale and shift parameters during training, with which we are then able to constrain the relative poses between consecutive frames. This constraint is achieved using our proposed novel loss functions. Experiments on real-world indoor and outdoor scenes show that our method can handle challenging camera trajectories and outperforms existing methods in terms of novel view rendering quality and pose estimation accuracy. Our project page is https://nope-nerf.active.vision.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2212.07388")
get_code_for_paper("2212.07388")
have("2212.07388")
Connect an agent — have() is free.