🛰️ Daily AI Frontier
‹ back to 2026-08-02

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

Research Multimodal & Generative

Ranking

Overall 81
Content 85
Popularity 71

Observed public metrics from 1 member.

Merged summary

TL;DR - TARS is a 3D-free, text-controlled video re-shooting method that changes camera motion, viewpoint, shot scale, and perspective without paired trajectory data or explicit 3D reconstruction. It improves control and temporal consistency while synthesizing content beyond the original view.

  • Sensitivity analysis finds that camera motion is mainly established during high-noise diffusion stages.
  • Self-supervised training learns camera dynamics and visual representations without paired re-shooting videos.
  • Joint text and camera conditioning enables reverse angles, large camera movements, and first-/third-person switching.
  • Experiments report more accurate and temporally consistent camera control than prior methods.

Sources (1)

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

arXiv cs.CV Jiwen Liu, Shujuan Li, Xiaohan Li, Zijie Meng, Xinyue Liu, Yulong Xu, Yan Zhou, Guoxin Zhang 2026-07-30 arXiv:2607.28261
Public signals Hugging Face upvotes 116
Providers: Hugging Face · Upvotes 116 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-08-31 14:29:54.405967 UTC

TL;DR - TARS is a 3D-free, text-controlled video re-shooting method that changes camera motion, viewpoint, shot scale, and perspective without paired trajectory data or explicit 3D reconstruction. It improves control and temporal consistency while synthesizing content beyond the original view.

  • Sensitivity analysis finds that camera motion is mainly established during high-noise diffusion stages.
  • Self-supervised training learns camera dynamics and visual representations without paired re-shooting videos.
  • Joint text and camera conditioning enables reverse angles, large camera movements, and first-/third-person switching.
  • Experiments report more accurate and temporally consistent camera control than prior methods.
item →