4 papers
Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation
Yuhang Zhang, Zhengyu Zhang, Muxin Liao +4
Generalizable semantic segmentation aims to perform well on unseen target domains, a critical challenge due to real-world applications requiring high generalizability. Class-wise p…
Depth-Sensitive Soft Suppression with RGB-D Inter-Modal Stylization Flow for Domain Generalization Semantic Segmentation
Binbin Wei, Yuhang Zhang, Shishun Tian +3
Unsupervised Domain Adaptation (UDA) aims to align source and target domain distributions to close the domain gap, but still struggles with obtaining the target data. Fortunately,…
Evaluating Human Perception of Novel View Synthesis: Subjective Quality Assessment of Gaussian Splatting and NeRF in Dynamic Scenes
Yuhang Zhang, Joshua Maraval, Zhengyu Zhang +3
Gaussian Splatting (GS) and Neural Radiance Fields (NeRF) are two groundbreaking technologies that have revolutionized the field of Novel View Synthesis (NVS), enabling immersive p…
Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation
Muxin Liao, Shishun Tian, Yuhang Zhang +3
Prototypical contrastive learning (PCL) has been widely used to learn class-wise domain-invariant features recently. These methods are based on the assumption that the prototypes,…