9 papers
URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation
Guoan Xu, Zhengxue Wang, Yang Xiao +3
Previous RGB-D semantic segmentation methods commonly employ dual encoders to separately process RGB and depth inputs, followed by dedicated modules for cross-modal feature fusion.…
DF: World Modeling via Decoder-Free Feature Forecasting in Autonomous Navigation
Jiaming Chen, Guoan Xu, Aoshen Huang +3
Forecasting future states from video sequences is a critical challenge for autonomous robotic systems and a fundamental objective of world modeling. Prior generative methods operat…
SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation
Guoan Xu, Jiaming Chen, Wenfeng Huang +3
The Vision Transformer (ViT) has achieved notable success in computer vision, with its variants widely validated across various downstream tasks, including semantic segmentation. H…
RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation
Guoan Xu, Yang Xiao, Guangwei Gao +3
Multimodal semantic segmentation has emerged as a powerful paradigm for enhancing scene understanding by leveraging complementary information from multiple sensing modalities (e.g.…
S2AFormer: Strip Self-Attention for Efficient Vision Transformer
Guoan Xu, Wenfeng Huang, Wenjing Jia +3
Vision Transformer (ViT) has made significant advancements in computer vision, thanks to its token mixer's sophisticated ability to capture global dependencies between all tokens.…
ReviveDiff: A Universal Diffusion Model for Restoring Images in Adverse Weather Conditions
Wenfeng Huang, Guoan Xu, Wenjing Jia +2
Images captured in challenging environments--such as nighttime, smoke, rainy weather, and underwater--often suffer from significant degradation, resulting in a substantial loss of…