4 papers
Unsupervised Stereo via Multi-Baseline Geometry-Consistent Self-Training
Peng Xu, Zhiyu Xiang, Tingming Bai +5
Photometric loss and pseudo-label-based self-training are two widely used methods for training stereo networks on unlabeled data. However, they both struggle to provide accurate su…
CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection
Hanzhi Zhong, Zhiyu Xiang, Ruoyu Xu +6
4D radar has received significant attention in autonomous driving thanks to its robustness under adverse weathers. Due to the sparse points and noisy measurements of the 4D radar,…
MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching
Peng Xu, Zhiyu Xiang, Jingyun Fu +3
Despite the significant advances in domain generalized stereo matching, existing methods still exhibit domain-specific preferences when transferring from synthetic to real domains,…
SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection
Ruoyu Xu, Zhiyu Xiang, Chenwei Zhang +6
3D object detection is one of the fundamental perception tasks for autonomous vehicles. Fulfilling such a task with a 4D millimeter-wave radar is very attractive since the sensor i…