PandaSet
PulseAugur coverage of PandaSet — every cluster mentioning PandaSet across labs, papers, and developer communities, ranked by signal.
-
AutoExpert system automates 3D LiDAR annotation for autonomous driving
Researchers have developed AutoExpert, a novel system designed to automate the process of 3D LiDAR annotation for autonomous driving datasets. This system aims to reduce the labor, tedium, and cost associated with tradi…
-
3D Gaussian Splatting for Self-Driving Simulation Implemented in Pure PyTorch
Researchers have developed a method to implement 3D Gaussian Splatting (3DGS) for self-driving simulation entirely in PyTorch, eliminating the need for custom CUDA kernels. This approach allows the entire training and r…
-
New 3D Gaussian Splatting Methods Enhance Driving Scene Reconstruction
Two new research papers introduce novel approaches to single-frame surround-view driving reconstruction using 3D Gaussian splatting. The first paper, VGGD, leverages visual geometry foundation models to improve geometri…
-
New L2D2-GS framework improves dynamic scene reconstruction
Researchers have developed L2D2-GS, a novel framework for dynamic Gaussian scene reconstruction that addresses the scalability limitations of existing methods. Unlike previous approaches that rely on expensive per-scene…
-
DrivingVoxels framework enhances dynamic scene reconstruction
Researchers have introduced DrivingVoxels, a new framework designed to improve the reconstruction of dynamic driving scenes. This method addresses limitations in existing approaches, such as the time-consuming nature of…
-
LA-Pose uses latent action pretraining for efficient camera pose estimation
Researchers have introduced LA-Pose, a novel approach to camera pose estimation that leverages self-supervised pretraining. This method utilizes inverse-dynamics models to learn latent action representations from large-…