collaborators

17 papers

cs.CV2025

EdgeSAM: Prompt-In-the-Loop Distillation for SAM

Chong Zhou, Xiangtai Li, Chen Change Loy +1

This paper presents EdgeSAM, an accelerated variant of the Segment Anything Model (SAM), optimized for efficient execution on edge devices with minimal compromise in performance. O…

cs.CV2025

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer

Qingyu Shi, Jianzong Wu, Jinbin Bai +4

The motion transfer task aims to transfer motion from a source video to newly generated videos, requiring the model to decouple motion from appearance. Previous diffusion-based met…

cs.CV2025

DreamRelation: Bridging Customization and Relation Generation

Qingyu Shi, Lu Qi, Jianzong Wu +4

Customized image generation is essential for creating personalized content based on user prompts, allowing large-scale text-to-image diffusion models to more effectively meet indiv…

cs.CV2025

Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language

Yicheng Chen, Xiangtai Li, Yining Li +4

Diffusion models can generate realistic and diverse images, potentially facilitating data availability for data-intensive perception tasks. However, leveraging these models to boos…

cs.CV2025

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Jianzong Wu, Chao Tang, Jingbo Wang +3

Story visualization, the task of creating visual narratives from textual descriptions, has seen progress with text-to-image generation models. However, these models often lack effe…

cs.CV2025

Explore In-Context Segmentation via Latent Diffusion Models

Chaoyang Wang, Xiangtai Li, Henghui Ding +5

In-context segmentation has drawn increasing attention with the advent of vision foundation models. Its goal is to segment objects using given reference images. Most existing appro…