SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.03725 · ICCV · 2021

I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling

Dong Yang, Ping Chen, Qin Li, Yong Tan, Yujin Chen, Fangyin Wu, Qingpei Xia

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

We propose a novel Image-to-UV prediction network (I2UV-HandNet) that estimates accurate and high-fidelity hand mesh from a single RGB image. Here, we present example results on the HO-3D dataset (left) and the FreiHAND dataset (right). From left to right: input, estimated coarse mesh, estimated high-fidelity mesh (in two viewpoints).

For agents

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

get_harvested_code_for_paper("2102.03725")
get_code_for_paper("2102.03725")
have("2102.03725")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2102.03725.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2102.03725.svg)](https://syntology.ai/paper/2102.03725)

Connect an agent — have() is free.