activity
20242026
collaborators

7 papers

cs.CV2026

Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

Xue Wu, Kang Zhao, Kafeng Wang +4

Diffusion-based methods have achieved impressive performance in real-world image super-resolution (Real-ISR) by leveraging large pre-trained stable diffusion (SD) models as powerfu…

cs.CV2026

MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts

Nuoyan Zhou, Zhijun Tu, Lei Yu +4

Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation. However,…

cs.CV2025

Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution

Xiao He, Zhijun Tu, Kun Cheng +4

The demonstrated success of sparsely-gated Mixture-of-Experts (MoE) architectures, exemplified by models such as DeepSeek and Grok, has motivated researchers to investigate their a…

cs.CV2025

3D Test-time Adaptation via Graph Spectral Driven Point Shift

Xin Wei, Qin Yang, Yijie Fang +2

While test-time adaptation (TTA) methods effectively address domain shifts by dynamically adapting pre-trained models to target domain data during online inference, their applicati…

cs.CV2025

TeSG: Textual Semantic Guidance for Infrared and Visible Image Fusion

Mingrui Zhu, Xiru Chen, Xin Wei +2

Infrared and visible image fusion (IVF) aims to combine complementary information from both image modalities, producing more informative and comprehensive outputs. Recently, text-g…

cs.CV2025

One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation

Xue Wu, Jingwei Xin, Zhijun Tu +4

Diffusion-based models have been widely used in various visual generation tasks, showing promising results in image super-resolution (SR), while typically being limited by dozens o…