5 papers
CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection
Yuchen Wu, Kun Wang, Yining Pan +1
Multi-modal fusion has emerged as a promising paradigm for accurate 3D object detection. However, performance degrades substantially when deployed in target domains different from…
Robust Depth Super-Resolution via Adaptive Diffusion Sampling
Kun Wang, Yun Zhu, Pan Zhou +1
We propose AdaDS, a generalizable framework for depth super-resolution that robustly recovers high-resolution depth maps from arbitrarily degraded low-resolution inputs. Unlike con…
Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance
Junkai Fan, Jiangwei Weng, Kun Wang +4
Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especia…
Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
Zhiqiang Yan, Zhengxue Wang, Kun Wang +2
In this paper, we introduce the Selective Image Guided Network (SigNet), a novel degradation-aware framework that transforms depth completion into depth enhancement for the first t…
Learning Inverse Laplacian Pyramid for Progressive Depth Completion
Kun Wang, Zhiqiang Yan, Junkai Fan +2
Depth completion endeavors to reconstruct a dense depth map from sparse depth measurements, leveraging the information provided by a corresponding color image. Existing approaches…