SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.16752 · CVPR · 2024

TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

Yu Sun, Yao Feng, Michael Black, Priyanka Patel, Sai Kumar Dwivedi

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

Meshcapade 3 ETH Zurich Figure 1. Existing methods for 3D human pose and shape (HPS) regression (e.g. HMR2.0 [11]) estimate bodies that are either imagealigned or have accurate 3D pose, but not both. We show that this is a fundamental trade-off for existing methods. To address this, TokenHMR, introduces a novel loss, Threshold-Adaptive Loss Scaling (TALS), and a discrete token-based pose representation of 3D pose. With these, TokenHMR achieves state-of-the-art accuracy on multiple in-the-wild 3D benchmarks. The circled regions compare poses.

For agents

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

get_harvested_code_for_paper("2404.16752")
get_code_for_paper("2404.16752")
have("2404.16752")

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

curl https://syntology.ai/api/ran/2404.16752.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.16752.svg)](https://syntology.ai/paper/2404.16752)

Connect an agent — have() is free.