2 papers
cs.CV2026
Improving Reconstruction of Representation Autoencoder
Siyu Liu, Chujie Qin, Hubery Yin +6
Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are…
cs.CV2025
RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration
Zilong Zhang, Chujie Qin, Chunle Guo +4
This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understand…