SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.16160 · CVPR · 2023

One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer

Lei Zhang, Yu Li, Jing Lin, Haoqian Wang, Ailing Zeng

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 3 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
IDEA-Research/OSX canonical 3 of 3
FunctionStatusWhere it lives
make_conv_layers Ran IDEA-Research/OSX/common/nets/layer.py
code served (permissive licence) · get_code("622140af456ff5d2")
make_deconv_layers Ran IDEA-Research/OSX/common/nets/layer.py
code served (permissive licence) · get_code("3a26e5305cd9fa2b")
make_linear_layers Ran IDEA-Research/OSX/common/nets/layer.py
code served (permissive licence) · get_code("6309528f3f76d031")

Repositories linked to this paper

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

Abstract

Fusion E D (a) Previous multi-stage pipeline (b) Our one-stage pipeline Figure 1. A comparison of existing whole-body mesh recovery methods and ours. Most existing methods leverage a multi-stage pipeline which uses separate expert models to process body component (e.g., E1: HeadNet, E2: HandNet, E3: BodyNet) and fuse them to get the whole-body prediction in a copy-paste manner. The result (from [36]) produces unnatural wrist poses. In contrast, our pipeline is a neat one-stage framework with a single encoder-decoder and can predict more accurately with natural meshes.

For agents

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

get_harvested_code_for_paper("2303.16160")
get_code_for_paper("2303.16160")
have("2303.16160")

Connect an agent — have() is free.