activity
20242026
collaborators

10 papers

cs.CV2026

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

Shuai Yang, Bingjie Gao, Ziwei Liu +3

Consistent video generation under editing operations requires persistence: when edits modify scene appearance or layout, subsequent generations should remain coherent across time a…

cs.CV2026

Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion

Weichen Fan, Haiwen Diao, Penghao Wu +1

Pixel-space diffusion models are trained on full-bandwidth noisy images, yet the useful signal available to the denoiser is strongly frequency dependent. Under rectified-flow diffu…

cs.CV2026

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Weichen Fan, Haiwen Diao, Quan Wang +2

Deep representations across modalities are inherently intertwined. In this paper, we systematically analyze the spectral characteristics of various semantic and pixel encoders. Int…

cs.CV2025

Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

Yuhan Zhang, Long Zhuo, Ziyang Chu +5

Despite rapid advances in 3D content generation, quality assessment for the generated 3D assets remains challenging. Existing methods mainly rely on image-based metrics and operate…

cs.CV2025

Video World Models with Long-term Spatial Memory

Tong Wu, Shuai Yang, Ryan Po +4

Emerging world models autoregressively generate video frames in response to actions, such as camera movements and text prompts, among other control signals. Due to limited temporal…

cs.CV2025

GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography

Mengchen Zhang, Tong Wu, Jing Tan +3

Camera trajectory design plays a crucial role in video production, serving as a fundamental tool for conveying directorial intent and enhancing visual storytelling. In cinematograp…