collaborators

7 papers

cs.CV2026

DreamLoop: Controllable Cinemagraph Generation from a Single Photograph

Aniruddha Mahapatra, Long Mai, Cusuh Ham +1

Cinemagraphs, which combine static photographs with selective, looping motion, offer unique artistic appeal. Generating them from a single photograph in a controllable manner is pa…

cs.CV2025

Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation

Yuan Yao, Yicong Hong, Difan Liu +3

The quadratic computational complexity of self-attention in diffusion transformers (DiT) introduces substantial computational costs in high-resolution image generation. While the l…

cs.CV2025

CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition

Quynh Phung, Long Mai, Fabian David Caba Heilbron +3

We present CineVerse, a novel framework for the task of cinematic scene composition. Similar to traditional multi-shot generation, our task emphasizes the need for consistency and…

cs.CV2025

REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder

Yitian Zhang, Long Mai, Aniruddha Mahapatra +5

We present a novel perspective on learning video embedders for generative modeling: rather than requiring an exact reproduction of an input video, an effective embedder should focu…

cs.CV2025

MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation

Jinbo Xing, Long Mai, Cusuh Ham +5

This paper presents a method that allows users to design cinematic video shots in the context of image-to-video generation. Shot design, a critical aspect of filmmaking, involves m…

cs.CV2025

Pushing the Boundaries of State Space Models for Image and Video Generation

Yicong Hong, Long Mai, Yuan Yao +1

While Transformers have become the dominant architecture for visual generation, linear attention models, such as the state-space models (SSM), are increasingly recognized for their…