AI Paper Atlas

Research map / 3D vision / Human pose estimation

SPEC: Seeing People in the Wild With an Estimated Camera

Muhammed Kocabas, Chun-Hao P. Huang, Joachim Tesch, Lea Müller, Otmar Hilliges, Michael J. Black

ICCV 2021 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 147 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
add Softargmax-L2 loss instead of KL loss (ablation)CamCalib · Pano360 testvfov error (deg): 3.53 -> 3.34Improved
add asymmetric biased loss for vfov (ablation)CamCalib · Pano360 testvfov error (deg): 3.34 -> 3.24Improved
add camera rotation Rc in projection (ablation)HMR* · SPEC-SYNW-MPJPE (mm): 118.3 / 85.1 -> 77.2 / 77.2Improved
add camera conditioning of the regressor (ablation)HMR* + c + f + Rc · SPEC-SYNW-MPJPE (mm): 77.2 -> 74.9Improved
use image center as principal point (ablation)HMR* · SPEC-SYNW-MPJPE (mm): 128.7 / 96.4 -> 120.4 / 84.2Improved
add CamCalib focal length instead of 5000 (ablation)HMR* + c · SPEC-SYNW-MPJPE (mm): 120.4 / 84.2 -> 118.3 / 85.1Mixed
add camera conditioning (ablation)HMR* + c + f + Rc · 3DPW valW-MPJPE (mm): 102.7 -> 98.1Improved
replace HMR* with SPECHMR* · 3DPW testMPJPE (mm): 92.5 -> 96.5Hurt
replace HMR* with SPECHMR* · SPEC-SYNW-MPJPE (mm): 128.7 / 96.4 -> 74.9 / 74.9Improved
add estimated rotation Rc to SMPLify-X (ablation)SMPLify-X (CamCalib K) · SPEC-SYNW-MPJPE (mm): 136.5 / 116.4 -> 115.2 / 115.2Improved
use CamCalib K instead of f=5000 in SMPLify-X (ablation)SMPLify-X · SPEC-SYNW-MPJPE (mm): 168.9 / 149.5 -> 136.5 / 116.4Improved
use CamCalib K and Rc instead of f=5000 in SMPLify-XSMPLify-X · 3DPW valW-MPJPE (mm): 123.8 / 94.7 -> 95.5 / 95.5Mixed

Later papers that compared with this method

2 later accepted papers report SPEC as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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