Chandan Yeshwanth, Matthias Nießner, Angela Dai, Yueh-Cheng Liu
We lifted 1 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 |
|---|---|---|
| scannetpp/scannetpp | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| update_transforms_json | Ran | scannetpp/scannetpp/dslr/undistort.py pointer only (licence: NONE) · get_code("52fd868f36ce59b6") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Figure 1: ScanNet++ contains 460 high-resolution 3D reconstructions of indoor scenes with dense semantic and instance annotations, along with corresponding high-quality DSLR images and iPhone RGB-D sequences. The long-tail and multilabeled annotations enable fine-grained semantic understanding, while the high-quality and commodity RGB images enable benchmarking of novel view synthesis methods at scale.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2308.11417")
get_code_for_paper("2308.11417")
have("2308.11417")
Connect an agent — have() is free.