SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.11417 · ICCV · 2023

ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

Chandan Yeshwanth, Matthias Nießner, Angela Dai, Yueh-Cheng Liu

arXiv · PDF · Open in the Atlas

Code that ran

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.

RepositoryRoleRan
scannetpp/scannetpp canonical 1 of 1
FunctionStatusWhere it lives
update_transforms_json Ran scannetpp/scannetpp/dslr/undistort.py
pointer only (licence: NONE) · get_code("52fd868f36ce59b6")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

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.