SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.15273 · ICCV · 2023

DECO: Dense Estimation of 3D Human-Scene Contact In The Wild

Michael Black, Hongwei Yi, Shashank Tripathi, Dimitrios Tzionas, Agniv Chatterjee, Jean-Claude Passy

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 7 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
sha2nkt/deco — 7 of 12
FunctionStatusWhere it lives
BasicBlock Ran sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("aa08b1e9b931f4dd")
Classifier Ran sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("4c099b4d3a311a6f")
Cross_Att Ran sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("3fc2ad51ca7a1405")
Decoder Ran sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("5f277424861d148f")
HighResolutionModule Ran sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("a06fe498ccd35dab")
Self_Attn Ran sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("80c771b3b438e460")
get_cfg_defaults Ran sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("779c0baa2f2d2439")
DECO Not yet run sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("df75e7818b4fed38")
Encoder Not yet run sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("0d8376e8bee064b3")
PoseHighResolutionNet Not yet run sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("6fb96a9d4d5b6696")
get_pose_net Not yet run sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("8c72b232bd94f8d4")
hrnet_w32 Not yet run sha2nkt/deco/models/deco.py
pointer only (licence: NOASSERTION) · get_code("5e2070c53b6e1fcb")

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: Given an RGB image, DECO infers dense vertex-level 3D contacts on the full human body. To this end, it reasons about the contacting body parts, human-object proximity, and the surrounding scene context to infer 3D contact for diverse human-object and human-scene interactions. Blue areas show the inferred contact on the body, hands, and feet for each image.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.15273")
get_code_for_paper("2309.15273")
have("2309.15273")

Connect an agent — have() is free.