AI Paper Atlas

Research map / 3D vision / 3D generation

DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars

Xiong Haozhong, Yao Yu, Yu Zhou, Sidan DU

ECCV 2026 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 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 adaptive temporal regularization (ablation)DSAR · Near-distribution testPSNR: 29.3130 -> 31.7153Improved
add adaptive temporal regularization (ablation)DSAR · Far-distribution testPSNR: 28.8778 -> 30.6720Improved
add geometric stream (previous deformation feedback) (ablation)DSAR · Far-distribution testPSNR: 24.2694 -> 30.6720Improved
add geometric stream (previous deformation feedback) (ablation)DSAR · Near-distribution testPSNR: 28.9622 -> 31.7153Improved
add state stream (memory bank) (ablation)DSAR · Far-distribution testPSNR: 28.2286 -> 30.6720Improved
add state stream (memory bank) (ablation)DSAR · Near-distribution testPSNR: 30.2593 -> 31.7153Improved
add velocity map (ablation)DSAR · Far-distribution testFVD: 1.87 -> 0.23Improved
use causal attention instead of bidirectional attention (ablation)DSAR · Far-distribution testFVD: 5.31 -> 0.23Improved
use memory bank state stream instead of direct cross-attention on previous frame (ablation)DSAR · Far-distribution testFVD: 2.14 -> 0.23Improved
add motion embedding (ablation)DSAR · Far-distribution testFVD: 1.94 -> 0.23Improved
use state stream instead of long skeletal pose history (ablation)DSAR · Far-distribution testFVD: 6.86 -> 0.23Improved
condition on deformations of previous 3 frames instead of one (ablation)DSAR · Far-distribution testPSNR: 30.6720 -> 30.7161No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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