SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.10180 · CVPR · 2024

MeshPose: Unifying DensePose and 3D Body Mesh reconstruction

Himmy Tam, Iasonas Kokkinos, George Papandreou, Eric-Tuan Lê, Antonis Kakolyris, Petros Koutras, Efstratios Skordos, Rıza Güler

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. The repositories linked to it are listed below.

Repositories linked to this paper

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

Abstract

meshpose.github.io DensePose PARE CLIFF NIKI MeshPose -Mesh MeshPose -UV Input Figure 1 . DensePose prediction systems are pixel-accurate but do not provide a 3D mesh, while human mesh recovery systems do not provide pixel-accurate 2D reprojection. We propose MeshPose, a novel human mesh recovery method that combines the benefits of both.

For agents

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

get_harvested_code_for_paper("2406.10180")
get_code_for_paper("2406.10180")
have("2406.10180")

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

curl https://syntology.ai/api/ran/2406.10180.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.10180.svg)](https://syntology.ai/paper/2406.10180)

Connect an agent — have() is free.