5 papers
LiAuto-GeoX: Efficient Grounded Driving Transformer
Jiawei Lian, Haoyi Sun, Yang Wu +8
Dense 3D reconstruction has demonstrated immense potential for spatial understanding, yet its viability as a real-time, onboard representation for autonomous driving remains an ope…
AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection
Yangting Shi, Yinfei Zhu, Renjie He +4
Omni-domain infrared small target detection (Omni-IRSTD) poses formidable challenges, as a single model must seamlessly adapt to diverse imaging systems, varying resolutions, and m…
Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection
Yun Zhu, Le Hui, Hang Yang +3
Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes wit…
Sketchy Bounding-box Supervision for 3D Instance Segmentation
Qian Deng, Le Hui, Jin Xie +1
Bounding box supervision has gained considerable attention in weakly supervised 3D instance segmentation. While this approach alleviates the need for extensive point-level annotati…
Deep Height Decoupling for Precise Vision-based 3D Occupancy Prediction
Yuan Wu, Zhiqiang Yan, Zhengxue Wang +3
The task of vision-based 3D occupancy prediction aims to reconstruct 3D geometry and estimate its semantic classes from 2D color images, where the 2D-to-3D view transformation is a…