Satoshi Ikehata
We lifted 8 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| satoshi-ikehata/sdm-unips-cvpr2023 | — | 1 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| PredictionHead | Ran | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("18c46000813125d3") |
| GLC_Aggregation | Not yet run | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("ab46129d2b2f846c") |
| GLC_Upsample | Not yet run | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("3d7b3b540b5e04c2") |
| ImageFeatureExtractor | Not yet run | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("29ae70b405dc9e43") |
| ImageFeatureFusion | Not yet run | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("45a21fe9e5c6bcb2") |
| Net | Not yet run | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("98f86a99159bc9cb") |
| Regressor | Not yet run | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("215a8657c68da22c") |
| ScaleInvariantSpatialLightImageEncoder | Not yet run | satoshi-ikehata/sdm-unips-cvpr2023/sdm_unips/modules/model/model.py pointer only (licence: NOASSERTION) · get_code("13ca5597f1641766") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Surface normal map SDM-UniPS (Ours) Input image (1st out of 9) UniPS [Ikehata2022] 3D Scanner (EinScan-SE) INPUT: Multiple images under varying unknown lighting conditions 1st 2nd 23rd Figure 1. Given multiple images under unknown spatially-varying illuminations, our method can recover the detailed surface normal map of non-convex, non-Lambertian surfaces (Left). Our method even surpasses the level of detail provided by consumer 3-D scanners (Right).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.15724")
get_code_for_paper("2303.15724")
have("2303.15724")
Connect an agent — have() is free.