AI Paper Atlas

Research map / Video / Video generation

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer

Hengye Lyu, Zisu Li, Yue Hong, Yueting Weng, Jiaxin Shi, Hanwang Zhang, Chen Liang

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 1 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 Self Forcing + DMD post-training to the causal student (ablation)RTR-DiT causal model · TV2V (50 Pexels videos)CLIP-T: 0.2284 -> 0.2585Improved
add Self Forcing + DMD post-training to the causal student (ablation)RTR-DiT causal model · RV2V (50 Pexels videos)CSD-Score: 0.6002 -> 0.7958Improved
add post-training to the causal student (ablation)RTR-DiT causal model · TV2V (50 Pexels videos)Aesthetic Quality: 0.5446 -> 0.6302Improved
add post-training to the causal student (ablation)RTR-DiT causal model · RV2V (50 Pexels videos)Imaging Quality: 0.6021 -> 0.7321Improved
add post-training to the causal student (ablation)RTR-DiT causal model · TV2V and RV2VCLIP-F: 0.9948 -> 0.9914 (TV2V); 0.9956 -> 0.9909 (RV2V)Hurt
distill bidirectional teacher into 2-step causal student (ablation)RTR-DiT · TV2V (50 Pexels videos)generation time (min): 1.43 -> 0.12Improved
distill bidirectional teacher into causal student (ablation)RTR-DiT · RV2V (50 Pexels videos)CSD-Score: 0.8050 -> 0.7958No clear effect
reference-preserving KV cache update (anchor reference at cache front) (ablation)RTR-DiT · long RV2V videosqualitative style consistencyImproved
use RTR-DiT instead of open-source TV2V baselinesRTR-DiT · TV2V (50 Pexels videos)CLIP-T: 0.2122 -> 0.2585 (vs TokenWarping)Improved
use RTR-DiT instead of commercial Gen-4 AlephRTR-DiT · RV2V (50 Pexels videos)CSD-Score: 0.8312 -> 0.7958Hurt
use RTR-DiT instead of Gen-4 AlephRTR-DiT · RV2V (50 Pexels videos)Aesthetic Quality: 0.6336 -> 0.6714Improved

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