Official checkpoints for Trans4trans: Efficient Transformer for Transparent Object & Scene Segmentation (ICCVW 2021, T-ITS 2022).
AI & ML interests
None defined yet.
Recent Activity
Organization Card
Integrated Sensing and Assistive Intelligence (InSAI) Lab
School of AI and Robotics, Hunan University (HNU)
"Building a utopia where integrated sensing systems empower and enhance human capabilities, especially benefiting people with disabilities."
🌟 Featured Open-Source Benchmarks & Models
🚗 DeLiVER & CMNeXt (CVPR 2023)
Arbitrary-modal semantic segmentation covering Depth, LiDAR, Events, Multiple Views, and RGB under 4 severe weather conditions and 5 sensor failure corner cases.
🌐 SynPASS & Trans4PASS / Trans4PASS+ (CVPR 2022)
Distortion-aware Vision Transformers tailored for 360° panoramic cameras and omnidirectional scene understanding, featuring the 9,080-frame SynPASS benchmark.
🚨 DADA-seg & ISSAFE / EDCNet (IROS 2021 & T-ITS 2021)
Dynamic event-driven semantic segmentation for traffic accident scenes under extreme dynamics and motion blur, featuring the pixel-annotated DADA-seg benchmark.
🗺️ 360BEV & 360Mapper (WACV 2024)
End-to-end panoramic semantic mapping to indoor Bird's-Eye View (BEV) with panoramic attention mechanisms and multi-scale indoor benchmarks (Stanford-360 & Matterport-360).
🗺️ Trans4Map (WACV 2023)
Transformer-based incremental semantic mapping from egocentric observations to top-down 2D floorplans with bounding sphere attention on Matterport3D.
🔍 MatchFormer (ACCV 2022 Oral)
Hierarchical extract-and-match transformer interleaving self- and cross-attention for robust indoor (ScanNet) and outdoor (MegaDepth) local feature matching.
👓 Trans4Trans (ICCVW 2021 & IEEE T-ITS 2022)
Efficient transformer system for transparent object segmentation and navigation assistance with Intel RealSense sensing and acoustic feedback.
🎯 Core Research Directions
- Multimodal Perception & Scene Understanding: Vision-Language Modeling, 2D/3D Vision, and sensor fusion in complex, adverse real-world environments.
- Autonomous Systems & Panoramic Vision: Semantic Mapping, Panoramic Sensing, Distortion-aware Transformers, and Bird’s-Eye-View (BEV) perception.
- Embodied Intelligence: Perception, navigation, and decision-making linking foundation models with robotic action, including Sim2Real adaptation.
- Assistive Technologies: Wearable assistive systems, navigation aids, and accessible interfaces designed around human capabilities.
- Brain-Computer Interface & Document Understanding: Cognitive state sensing, assistive BCI, and intelligent layout/reading assistance.
models 7
InSAI-Lab/Trans4trans
Image Segmentation • Updated
InSAI-Lab/MatchFormer
Updated
InSAI-Lab/Trans4Map
Image Segmentation • Updated
InSAI-Lab/360BEV
Image Segmentation • Updated
InSAI-Lab/ISSAFE
Image Segmentation • Updated
InSAI-Lab/CMNeXt
Image Segmentation • Updated
InSAI-Lab/Trans4PASS
Image Segmentation • Updated