AI Paper Atlas

Research map / Video / Video generation

STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits

Foivos Paraperas Papantoniou, Stathis Galanakis, Rolandos Alexandros Potamias, Bernhard Kainz, Stefanos Zafeiriou

ICML 2026 · Video › Video generation · approach: Diffusion-based human image animation · 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 lip-reading loss (ablation)STARCaster · TH-1KHLSE-C: 5.140 -> 5.493Improved
add lip-reading loss (ablation)STARCaster · TH-1KHLSE-D: 9.016 -> 8.724Improved
add self-forcing instead of teacher forcing (ablation)STARCaster · TH-1KHPose Std (x10^-2): 4.386 -> 4.896Improved
add self-forcing instead of teacher forcing (ablation)STARCaster · TH-1KHFVD: 197.28 -> 185.24Improved
add self-forcing instead of teacher forcing (ablation)STARCaster · Hallo3Pose Std (x10^-2): 4.161 -> 4.760Improved
use progressive training stages instead of a single autoregressive stage (ablation)STARCaster · Hallo3FVD: 152.98 -> 145.35Improved
use progressive training instead of a single stage (ablation)STARCaster · Hallo3LSE-C: 6.233 -> 6.292No clear effect
drive generation by ID embedding only without portrait referenceSTARCaster · TH-1KHLSE-C: 5.493 -> 5.627Improved
use lightweight SD-UNet backbone instead of 5B DiT (Hallo3)audio-driven animation · 5-second clip inferenceinference time (min): 21.4 -> 2.2Improved
use implicit video-based view synthesis instead of 3D inversion (Real3DPortrait)3D-aware talking portraits · NeRSemblePSNR: 10.289 -> 14.219Improved

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