Search Results for author:
Found 12 papers, 8 papers with code
Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
This paper proposes an equivariant neural network that takes data in any semi-simple Lie algebra as input.
4D Panoptic Segmentation as Invariant and Equivariant Field Prediction
In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation.
MonoEdge: Monocular 3D Object Detection Using Local Perspectives
We propose a novel approach for monocular 3D object detection by leveraging local perspective effects of each object.
Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection
Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4. 65% improvement on AP@0. 7 for car detection, reaching 18. 54% AP@0. 7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard.
E2PN: Efficient SE(3)-Equivariant Point Network
We also propose a permutation layer to recover SO(3) features from spherical features to preserve the capacity to distinguish rotations.
Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations
We learn an embedding for each point cloud in a feature space that preserves the SO(3)-equivariance property, enabled by recent developments in equivariant neural networks.
VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars
A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper.
Lite-FPN for Keypoint-based Monocular 3D Object Detection
3D object detection with a single image is an essential and challenging task for autonomous driving.
Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography
This paper proposes a method to extract the position and pose of vehicles in the 3D world from a single traffic camera.
Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss
Object detection and tracking is a key task in autonomy.
Monocular Depth Prediction through Continuous 3D Loss
In contrast to the current point-to-point loss evaluation approach, the proposed 3D loss treats point clouds as continuous objects; therefore, it compensates for the lack of dense ground truth depth due to LIDAR's sparsity measurements.
Mcity Data Collection for Automated Vehicles Study
The main goal of this paper is to introduce the data collection effort at Mcity targeting automated vehicle development.
