6 papers
UniT: Unified Geometry Learning with Group Autoregressive Transformer
Haotian Wang, Yusong Huang, Zhaonian Kuang +4
Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essential capabilities remain fra…
CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection
Zhaonian Kuang, Rui Ding, Haotian Wang +3
Multi-camera 3D object detection (MC3D) has attracted increasing attention with the growing deployment of multi-sensor physical agents, such as robots and autonomous vehicles. Howe…
PNav: End-to-End Perception, Prediction and Planning for Vision-and-Language Navigation
Tianfu Li, Wenbo Chen, Haoxuan Xu +2
In Vision-and-Language Navigation (VLN), an agent is required to plan a path to the target specified by the language instruction, using its visual observations. Consequently, preva…
RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection
Rui Ding, Zhaonian Kuang, Zongwei Zhou +3
Multi-view 3D detection with bird's eye view (BEV) is crucial for autonomous driving and robotics, but its robustness in real-world is limited as it struggles to predict accurate d…
Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection
Rui Ding, Zhaonian Kuang, Yuzhe Ji +3
Multi-modal 3D object detection with bird's eye view (BEV) has achieved desired advances on benchmarks. Nonetheless, the accuracy may drop significantly in the real world due to da…
Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detection
Zhaonian Kuang, Rui Ding, Meng Yang +2
Monocular 3D object detection (M3OD) is intrinsically ill-posed, hence training a high-performance deep learning based M3OD model requires a humongous amount of labeled data with c…