8 papers · 1 filter
UNIV: Unified Foundation Model for Infrared and Visible Modalities
Fangyuan Mao, Shuo Wang, Jilin Mei +6
Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models excel within single modalities, th…
Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes
Shuo Wang, Jilin Mei, Fuyang Liu +6
Feedforward Gaussian Splatting has recently emerged as an efficient paradigm for 4D reconstruction in autonomous driving. However, in unstructured off-road scenes, its performance…
Towards All-Day Perception for Off-Road Driving: A Large-Scale Multispectral Dataset and Comprehensive Benchmark
Shuo Wang, Jilin Mei, Wenfei Guan +4
Off-road nighttime autonomous driving suffers from unreliable visible-light perception, making infrared modality crucial for accurate freespace detection. However, progress remains…
SSI-DM: Singularity Skipping Inversion of Diffusion Models
Chen Min, Enze Jiang, Jishen Peng +1
Inverting real images into the noise space is essential for editing tasks using diffusion models, yet existing methods produce non-Gaussian noise with poor editability due to the i…
Beyond Endpoints: Path-Centric Reasoning for Vectorized Off-Road Network Extraction
Wenfei Guan, Jilin Mei, Tong Shen +4
Deep learning has advanced vectorized road extraction in urban settings, yet off-road environments remain underexplored and challenging. A significant domain gap causes advanced mo…
OT-Drive: Out-of-Distribution Off-Road Traversable Area Segmentation via Optimal Transport
Zhihua Zhao, Guoqiang Li, Chen Min +1
Reliable traversable area segmentation in unstructured environments is critical for planning and decision-making in autonomous driving. However, existing data-driven approaches oft…