SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.02753 · 2021

MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 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
SeanChenxy/HandMesh canonical 7 of 9
FunctionStatusWhere it lives
bce_loss Ran SeanChenxy/HandMesh/cmr/models/loss.py
code served (permissive licence) · get_code("0a345c9ad82f11fa")
conv1x1 Ran SeanChenxy/HandMesh/cmr/models/resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
conv3x3 Ran SeanChenxy/HandMesh/cmr/models/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
conv_layer Ran SeanChenxy/HandMesh/cmr/models/network_mobrecon.py
code served (permissive licence) · get_code("88c9b7333f9e5e69")
l1_loss Ran SeanChenxy/HandMesh/cmr/models/loss.py
code served (permissive licence) · get_code("52873d5d0dc3cad5")
linear_layer Ran SeanChenxy/HandMesh/cmr/models/network_mobrecon.py
code served (permissive licence) · get_code("a29a058e008b55a9")
resnet18 Ran SeanChenxy/HandMesh/cmr/models/resnet.py
code served (permissive licence) · get_code("23b518f1014a72f5")
Pool Not yet run SeanChenxy/HandMesh/cmr/models/network_mobrecon.py
code served (permissive licence) · get_code("21126d9705e3eae1")
normal_loss Not yet run SeanChenxy/HandMesh/cmr/models/loss.py
code served (permissive licence) · get_code("f82aaf02ccad7316")

Repositories linked to this paper

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

Abstract

In this work, we propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence. Specifically, for 2D encoding, we propose lightweight yet effective stacked structures. Regarding 3D decoding, we provide an efficient graph operator, namely depth-separable spiral convolution. Moreover, we present a novel feature lifting module for bridging the gap between 2D and 3D representations. This module begins with a map-based position regression (MapReg) block to integrate the merits of both heatmap encoding and position regression paradigms for improved 2D accuracy and temporal coherence. Furthermore, MapReg is followed by pose pooling and pose-to-vertex lifting approaches, which transform 2D pose encodings to semantic features of 3D vertices. Overall, our hand reconstruction framework, called MobRecon, comprises affordable computational costs and miniature model size, which reaches a high inference speed of 83FPS on Apple A14 CPU. Extensive experiments on popular datasets such as FreiHAND, RHD, and HO3Dv2 demonstrate that our MobRecon achieves superior performance on reconstruction accuracy and temporal coherence. Our code is publicly available at https://github.com/SeanChenxy/HandMesh.

For agents

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

get_harvested_code_for_paper("2112.02753")
get_code_for_paper("2112.02753")
have("2112.02753")

Connect an agent — have() is free.