7 papers
Radar-Informed 3D Multi-Object Tracking under Adverse Conditions
Bingxue Xu, Emil Hedemalm, Ajinkya Khoche +1
The challenge of 3D multi-object tracking is achieving robustness in real-world applications, for example under adverse conditions and maintaining consistency as distance increases…
Correcting and Quantifying Systematic Errors in 3D Box Annotations for Autonomous Driving
Alexandre Justo Miro, Ludvig af Klinteberg, Bogdan Timus +5
Accurate ground truth annotations are critical to supervised learning and evaluating the performance of autonomous vehicle systems. These vehicles are typically equipped with activ…
HiMo: High-Speed Objects Motion Compensation in Point Clouds
Qingwen Zhang, Ajinkya Khoche, Yi Yang +4
LiDAR point cloud is essential for autonomous vehicles, but motion distortions from dynamic objects degrade the data quality. While previous work has considered distortions caused…
BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining
Ajinkya Khoche, GergŠLászló Nagy, Maciej Wozniak +2
Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic da…
DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance
Ajinkya Khoche, Qingwen Zhang, Yixi Cai +2
Accurate 3D scene flow estimation is critical for autonomous systems to navigate dynamic environments safely, but creating the necessary large-scale, manually annotated datasets re…
SSF: Sparse Long-Range Scene Flow for Autonomous Driving
Ajinkya Khoche, Qingwen Zhang, Laura Pereira Sanchez +3
Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based percept…