AI Paper Atlas

Research map / 3D vision / Human pose estimation

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape

Jiacong Xu, Yi Zhang, Jiawei Peng, Wufei Ma, Artur Jesslen, Pengliang Ji, Qixin Hu, Jiehua Zhang, Qihao Liu, Jiahao Wang, Wei Ji, Chen Wang and 8 more

ICCV 2023 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 43 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pre-train on synthetic SMALR data before fine-tuning on Animal3DPARE · Animal3D testS-MPJPE (mm): 443.9 -> 392.3Improved
pre-train on synthetic data for HMRHMR · Animal3D testPA-MPJPE (mm): 140.7 -> 124.8Improved
initialize from human pose pre-trained modelsHMR and PARE · Animal3D testPA-MPJPE (mm): PARE 134.8 -> 130.7; HMR 140.7 -> 132.2Improved
use human pre-training instead of synthetic pre-trainingHMR and PARE · Animal3D testPA-MPJPE (mm): PARE 127.2 (synthetic) vs 130.7 (human); HMR 124.8 vs 132.2No clear effect
use animal-specific WLDO versus human models in supervised trainingWLDO · Animal3D testS-MPJPE (mm): PA-MPJPE 128.8 best; S-MPJPE 502.1 worstMixed
use part-segmentation supervision architecture PARE versus HMRPARE · Animal3D testPCK: 59.3 -> 79.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy