Related papers: Re-Evaluating LiDAR Scene Flow for Autonomous Driv…
Generative world models have become essential data engines for autonomous driving, yet most existing efforts focus on videos or occupancy grids, overlooking the unique LiDAR properties. Extending LiDAR generation to dynamic 4D world…
The proposal of Pseudo-Lidar representation has significantly narrowed the gap between visual-based and active Lidar-based 3D object detection. However, current researches exclusively focus on pushing the accuracy improvement of…
Estimating 3D scene flow from a sequence of monocular images has been gaining increased attention due to the simple, economical capture setup. Owing to the severe ill-posedness of the problem, the accuracy of current methods has been…
In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and…
LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on spatial alignment between LiDAR and camera sensors, they often…
Scene flow is the task of estimating 3D motion vectors to individual points of a dynamic 3D scene. Motion vectors have shown to be beneficial for downstream tasks such as action classification and collision avoidance. However, data…
Diffusion models have been applied to 3D LiDAR scene completion due to their strong training stability and high completion quality. However, the slow sampling speed limits the practical application of diffusion-based scene completion models…
Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically…
3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for…
LiDAR odometry plays an important role in self-localization and mapping for autonomous navigation, which is usually treated as a scan registration problem. Although having achieved promising performance on KITTI odometry benchmark, the…
Recent multimodal fusion methods, integrating images with LiDAR point clouds, have shown promise in scene flow estimation. However, the fusion of 4D millimeter wave radar and LiDAR remains unexplored. Unlike LiDAR, radar is cheaper, more…
Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable…
We propose a new multi-frame method for efficiently computing scene flow (dense depth and optical flow) and camera ego-motion for a dynamic scene observed from a moving stereo camera rig. Our technique also segments out moving objects from…
In this technical report we investigate speed estimation of the ego-vehicle on the KITTI benchmark using state-of-the-art deep neural network based optical flow and single-view depth prediction methods. Using a straightforward intuitive…
While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation methodology. Hence,…
Scene flow estimation is a crucial component in the development of autonomous driving and 3D robotics, providing valuable information for environment perception and navigation. Despite the advantages of learning-based scene flow estimation…
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 by ego motion, distortions caused by other moving objects…
Effective environment modeling is the foundation for autonomous driving, underpinning tasks from perception to planning. However, current paradigms often inadequately consider the feedback of ego motion to the observation, which leads to an…
There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR. The camera provides rich semantic information such as color, texture, and the LiDAR reflects the 3D shape and locations of surrounding…
Building LiDAR generative models holds promise as powerful data priors for restoration, scene manipulation, and scalable simulation in autonomous mobile robots. In recent years, approaches using diffusion models have emerged, significantly…