7 papers
Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation
Tianhao Guo, Bingjie Lu, Feng Wang +1
Single image super-resolution traditionally assumes spatially-invariant degradation models, yet real-world imaging systems exhibit complex distance-dependent effects including atmo…
CLIP-aware Domain-Adaptive Super-Resolution
Zhengyang Lu, Qian Xia, Weifan Wang +1
This work introduces CLIP-aware Domain-Adaptive Super-Resolution (CDASR), a novel framework that addresses the critical challenge of domain generalization in single image super-res…
Differentiable NMS via Sinkhorn Matching for End-to-End Fabric Defect Detection
Zhengyang Lu, Bingjie Lu, Weifan Wang +1
Fabric defect detection confronts two fundamental challenges. First, conventional non-maximum suppression disrupts gradient flow, which hinders genuine end-to-end learning. Second,…
CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference
Zhengyang Lu, Bingjie Lu, Feng Wang
Physical and optical factors interacting with sensor characteristics create complex image degradation patterns. Despite advances in deep learning-based super-resolution, existing m…
Single-image reflection removal via self-supervised diffusion models
Zhengyang Lu, Weifan Wang, Tianhao Guo +1
Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffers from the shortage of paired real-world samples.…
Semi-supervised Chinese Poem-to-Painting Generation via Cycle-consistent Adversarial Networks
Zhengyang Lu, Tianhao Guo, Feng Wang
Classical Chinese poetry and painting represent the epitome of artistic expression, but the abstract and symbolic nature of their relationship poses a significant challenge for com…