AI Paper Atlas

Research map / Video / Video generation

StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars

Zhiyao Sun, Ziqiao Peng, Yifeng Ma, Yi Chen, Zhengguang Zhou, Zixiang Zhou, Guozhen Zhang, Youliang Zhang, Yuan Zhou, Qinglin Lu, Yong-Jin Liu

CVPR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 23 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 Reference Sink to autoregressive student (ablation)StreamAvatar · Talking avatar long set (25 imgs, 20s)IQA: 4.01 -> 4.64Improved
add Reference Sink (ablation)StreamAvatar · Talking avatar short set (50 imgs, 5s)FID: 96.58 -> 88.75Improved
add RAPR positional re-encoding (ablation)StreamAvatar · Talking avatar short set (50 imgs, 5s)FID: 88.75 -> 81.63Improved
add RAPR positional re-encoding (ablation)StreamAvatar · Talking avatar long set (25 imgs, 20s)IQA: 4.64 -> 4.84Improved
add adversarial refinement with standard discriminator (ablation)StreamAvatar · Talking avatar short set (50 imgs, 5s)FID: 81.63 -> 79.68Improved
add adversarial refinement with standard discriminator (ablation)StreamAvatar · Talking avatar long set (25 imgs, 20s)HA: 0.961 -> 0.993Mixed
use consistency-aware discriminator instead of standard discriminator (ablation)StreamAvatar · Talking avatar short set (50 imgs, 5s)FID: 79.68 -> 74.21Improved
use consistency-aware discriminator instead of standard discriminator (ablation)StreamAvatar · Talking avatar long set (25 imgs, 20s)Sync-C: 6.38 -> 6.64Improved
apply audio mask to Wav2Vec features instead of raw audio (ablation)StreamAvatar (undistilled) · Interactive avatar audio mask positionLHKV: 15.49 -> 21.44Improved
add listening-audio modules vs silent-audio baselineOmniAvatar baseline · Interactive avatar (50 SpeakerVid-5M videos)LBKV: 6.05 -> 15.88Improved
3-step causal distilled model vs slower offline baselinesStreamAvatar · Talking avatar short set (50 imgs, 5s)FVD: 557.46 -> 707.34Hurt

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