AI Paper Atlas

Research map / 3D vision / Face and shape

EgoGVAE: Ego-body Mesh Reconstruction via Guided Variational Autoencoder

Jaehun Jung, Wonjun Kim

ECCV 2026 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 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 latent-distribution guidance from the motion-to-motion VAE (ablation)EgoGVAE head-to-motion network · AMASS (128 frames)MPJPE: 128.3 -> 113.7 in MPJPE and 110.3 -> 94.5 in PA-MPJPEImproved
add learnable tokens for unobserved body parts (ablation)EgoGVAE (with guidance) · AMASS (128 frames)MPJPE: 113.7 -> 106.7Improved
add learnable tokens without guidance (ablation)EgoGVAE baseline · AMASS (128 frames)MPJPE: 128.3 -> 125.6Improved
add L_normal_KL regularization toward standard normal (ablation)EgoGVAE · AMASS (128 frames)MPJPE: 114.6 -> 106.7Improved
add velocity loss L_vel (ablation)EgoGVAE · AMASS (128 frames)MPJPE: 109.8 -> 106.7Improved
align latent distributions via joint training instead of learning latent-to-latent mapping (ablation)EgoGVAE · AMASS (128 frames)MPJPE: 128.1 -> 106.7Improved
jointly train guidance network instead of using fixed pre-trained motion prior (ablation)EgoGVAE · AMASS (128 frames)MPJPE: 111.2 -> 106.7Improved
replace diffusion sampling (EgoAllo) with one-step VAE samplingEgoGVAE · Efficiency (128 frames)inference time: 1.510 -> 0.026 secondsImproved
EgoGVAE vs EgoAllo on AMASS head-onlyEgoGVAE · AMASS (128 frames)MPJPE: 119.7 -> 106.7Improved
EgoGVAE vs EgoAllo on RICH cross-datasetEgoGVAE · RICH (trained on AMASS)MPJPE: 193.1 -> 179.9Improved
EgoGVAE vs EgoAllo on real-world EgoBodyEgoGVAE · EgoBodyMPJPE: 172.9 -> 162.9Improved
EgoGVAE vs EgoEgo jitter on EgoBodyEgoGVAE · EgoBodyJitter: 1.40 vs 1.42No clear effect

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