2 papers
cs.CV2026
DACESR: Degradation-Aware Conditional Embedding for Real-World Image Super-Resolution
Xiaoyan Lei, Wenlong Zhang, Biao Luo +3
Multimodal large models have shown excellent ability in addressing image super-resolution in real-world scenarios by leveraging language class as condition information, yet their a…
cs.CV2025
DIFFUMA: High-Fidelity Spatio-Temporal Video Prediction via Dual-Path Mamba and Diffusion Enhancement
Xinyu Xie, Weifeng Cao, Jun Shi +4
Spatio-temporal video prediction plays a pivotal role in critical domains, ranging from weather forecasting to industrial automation. However, in high-precision industrial scenario…