AI Paper Atlas

Research map / 3D vision / Face and shape

AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors

Aymen Mir, Riza Alp Guler, Xiangjun Tang, Peter Wonka, Gerard Pons-Moll

ECCV 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 2 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 hallucination supervision and full pose-dependent avatar stage over coarse avatar (ablation)AHOY · BEHAVE novel viewPSNR: 16.10 -> 24.12Improved
add hallucination supervision and full avatar stage over coarse avatar (ablation)AHOY · BEHAVE novel posePSNR: 14.30 -> 22.81Improved
add RF-Inversion hallucinated video supervision (ablation)AHOY · BEHAVE novel viewPSNR: 21.10 -> 24.12Improved
add RF-Inversion hallucinated video supervision (ablation)AHOY · BEHAVE novel posePSNR: 19.40 -> 22.81Improved
add RF-Inversion hallucinated video supervision (ablation)AHOY · BEHAVE novel viewLPIPS: 0.143 -> 0.090Improved
add map-pose/LBS-pose decoupling (ablation)AHOY · BEHAVE novel viewPSNR: 22.60 -> 24.12Improved
add map-pose/LBS-pose decoupling (ablation)AHOY · BEHAVE novel posePSNR: 20.60 -> 22.81Improved
add map-pose/LBS-pose decoupling (ablation)AHOY · BEHAVE novel poseLPIPS: 0.152 -> 0.110Improved
add head/body split supervision (ablation)AHOY · BEHAVE novel viewPSNR: 23.60 -> 24.12Improved
add head/body split supervision (ablation)AHOY · BEHAVE novel posePSNR: 22.20 -> 22.81Improved
give baselines canonical-pose input instead of occluded input (LHM)AHOY · YouTube animationPSNR: 19.03 -> 20.17Improved
give AHOY canonical-pose instead of occluded inputAHOY · YouTube animationPSNR: 22.81 -> 22.83No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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