AI Paper Atlas

Research map / 3D vision / Human pose estimation

The One Where They Reconstructed 3D Humans and Environments in TV Shows

Georgios Pavlakos, Ethan Weber, Matthew Tancik, Angjoo Kanazawa

ECCV 2022 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 24 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 camera intrinsics and extrinsics to multi-shot optimization (calibrated vs uncalibrated) (ablation)multi-shot optimization · Human3.6MMPJPE (mm): 131.9 -> 65.8Improved
add extrinsics on top of intrinsics in multi-shot optimization (ablation)multi-shot optimization · Human3.6MMPJPE (mm): 123.8 -> 65.8Improved
add camera calibration to multi-shot optimization (ablation)multi-shot optimization · TV showspelvis distance error (cm): 889cm -> 38cmImproved
add extrinsics on top of intrinsics in multi-shot optimization (ablation)multi-shot optimization · TV showspelvis distance error (cm): 59cm -> 38cmImproved
add camera intrinsics to contextual monocular fitting (ablation)SMPLify with context · TV showscross-shot PCK (%): 16.0% -> 88.7%Improved
add body shape scale from neighboring shot change (ablation)SMPLify with context · TV showscross-shot PCK (%): 65.9% -> 88.7%Improved
add NeRF density structure term to avoid interpenetration (ablation)SMPLify with context · TV showscross-shot PCK (%): 87.5% -> 88.7%Improved
add full 3D context to SMPLifySMPLify · TV showscross-shot PCK (%): 16.5% -> 88.7%Improved
replace image-based re-ID costs with multi-shot fitting cost incl. anthropometric constraintsre-ID matching · TV shows shot-boundary re-IDRe-ID F1: 0.80 -> 0.91Improved
add anthropometric constraints to keypoint triangulation cost (ablation)re-ID matching · TV shows shot-boundary re-IDRe-ID F1: 0.86 -> 0.91Improved
use 3D human reconstruction for gaze instead of face-based gaze followinggaze estimation · TV shows gaze following (all)PCGD (%): 16% -> 62%Improved
use 3D human reconstruction for gaze instead of face-based gaze followinggaze estimation · TV shows gaze following (w/ face)PCGD (%): 32% -> 67%Improved

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