collaborators

6 papers

cs.CV2026

Self Gradient Forcing: Native Long Video Extrapolation

Junhao Zhuang, Shiyi Zhang, Yuxuan Bian +11

Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own rollout rather than ground-tru…

cs.CV2026

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

Jiwen Liu, Shujuan Li, Zhixue Fang +8

Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametr…

cs.CV2026

AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model

Yutian Chen, Shi Guo, Renbiao Jin +7

Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusion-based approaches m…

cs.CV2026

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Yawen Luo, Xiaoyu Shi, Junhao Zhuang +5

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotS…

cs.CV2025

CamCloneMaster: Enabling Reference-based Camera Control for Video Generation

Yawen Luo, Jianhong Bai, Xiaoyu Shi +6

Camera control is crucial for generating expressive and cinematic videos. Existing methods rely on explicit sequences of camera parameters as control conditions, which can be cumbe…

cs.CV2025

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

Qinghe Wang, Yawen Luo, Xiaoyu Shi +7

In this work, we present CineMaster, a novel framework for 3D-aware and controllable text-to-video generation. Our goal is to empower users with comparable controllability as profe…