Jointly processing information from multiple sensors is crucial to achie...
Motion prediction is crucial for autonomous driving systems to understan...
3D multi-object tracking (MOT) is vital for many applications including
...
Masked signal modeling has greatly advanced self-supervised pre-training...
With the prevalence of multimodal learning, camera-LiDAR fusion has gain...
Recently, virtual/pseudo-point-based 3D object detection that seamlessly...
Designing an efficient yet deployment-friendly 3D backbone to handle spa...
Although DETR-based 3D detectors can simplify the detection pipeline and...
We present a novel two-stage fully sparse convolutional 3D object detect...
Predicting multimodal future behavior of traffic participants is essenti...
In this report, we present the 1st place solution for motion prediction ...
Autonomous driving, in recent years, has been receiving increasing atten...
Despite substantial progress in 3D object detection, advanced 3D detecto...
Accurate and reliable 3D detection is vital for many applications includ...
As a fundamental problem in computer vision, 3D object detection is
expe...
Rapid progress in 3D semantic segmentation is inseparable from the advan...
Stereo-based 3D detection aims at detecting 3D object bounding boxes fro...
In this paper, we present a self-training method, named ST3D++, with a
h...
3D object detection in point clouds is a challenging vision task that
be...
We present a new domain adaptive self-training pipeline, named ST3D, for...
3D object detection is receiving increasing attention from both industry...
Recent advances on 3D object detection heavily rely on how the 3D data a...
In this technical report, we present the top-performing LiDAR-only solut...
Instance segmentation is an important task for scene understanding. Comp...
3D vehicle detection based on point cloud is a challenging task in real-...
We present a novel and high-performance 3D object detection framework, n...
In this paper, we propose the part-aware and aggregation neural network
...
A well-trained model should classify objects with a unanimous score for ...
In this paper, we propose PointRCNN for 3D object detection from raw poi...