AI Paper Atlas

Research map / 3D vision / Face and shape

PHOSA: Photorealistic 3D Sign Avatar Modeling and Benchmark

Haodong Wang, Hezhen Hu, Wengang Zhou, Houqiang Li

ECCV 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 0 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 hybrid SMPL-X fitting (HaMeR hands, INFERNO face) instead of DWPose-only fitting (ablation)avatar modeling · MVSign (Hand region)PSNR: 16.82 -> 18.85Improved
add hybrid SMPL-X fitting (ablation)avatar modeling · MVSign (Full body)PSNR: 23.58 -> 26.90Improved
increase training views from 1 to 16 (ablation)PHOSA · MVSign (Hand region)PSNR: 18.49 -> 18.85Improved
train on basic hand shapes only instead of both subsets (ablation)PHOSA · MVSign (Hand region)PSNR: 18.85 -> 17.47Hurt
train on sign sentences only instead of both subsets (ablation)PHOSA · MVSign (Hand region)PSNR: 18.85 -> 17.62Hurt
use motion-aware sampling instead of random sampling (ablation)PHOSA · MVSign (Hand region)PSNR: 17.40 -> 18.03Improved
use motion-aware sampling instead of sequential sampling (ablation)PHOSA · MVSign (Full body)PSNR: 26.55 -> 27.67Improved
decouple body, head and hand Gaussian maps (ablation)PHOSA · MVSign (Hand region)PSNR: 16.65 -> 17.53Improved
add partial kinematic decoupling for hands on top of decoupling (ablation)PHOSA · MVSign (Hand region)PSNR: 17.53 -> 18.74Improved
PHOSA vs best baseline on in-the-wild monocular videoPHOSA · In-the-wild monocular web video (Full body)PSNR: 19.61 -> 20.39Improved
PHOSA vs best baseline on MVSignPHOSA · MVSign multi-view (Full body)PSNR: 25.91 -> 27.03Improved

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