activity
20242026
collaborators
Showing cs.CVShow all

17 papers · 1 filter

cs.CV2026

ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization

Bingchen Li, Zhixin Wang, Fan Li +5

Old photos preserve invaluable historical memories, making their restoration and colorization highly desirable. While existing restoration models can address some degradation issue…

cs.CV2025

Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior

Ruoyu Feng, Yunpeng Qi, Jinming Liu +4

Image compression methods are usually optimized isolatedly for human perception or machine analysis tasks. We reveal fundamental commonalities between these objectives: preserving…

cs.CV2025

4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models

Yiting Lu, Wei Luo, Peiyan Tu +8

World Generation Models are emerging as a cornerstone of next-generation multimodal intelligence systems. Unlike traditional 2D visual generation, World Models aim to construct rea…

cs.CV2025

Test-Time Preference Optimization for Image Restoration

Bingchen Li, Xin Li, Jiaqi Xu +4

Image restoration (IR) models are typically trained to recover high-quality images using L1 or LPIPS loss. To handle diverse unknown degradations, zero-shot IR methods have also be…

cs.CV2025

P-4DGS: Predictive 4D Gaussian Splatting with 90 Compression

Henan Wang, Hanxin Zhu, Xinliang Gong +3

3D Gaussian Splatting (3DGS) has garnered significant attention due to its superior scene representation fidelity and real-time rendering performance, especially for dynamic 3D sce…

cs.CV2025

Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent

Yixin Gao, Xin Li, Xiaohan Pan +7

We present Comp-X, the first intelligently interactive image compression paradigm empowered by the impressive reasoning capability of large language model (LLM) agent. Notably, com…