VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction
This addresses perception challenges in autonomous driving by integrating multiple sensor modalities, though it is incremental as it builds on existing depth prediction and object detection techniques.
The paper tackles joint 3D object detection and monocular dense depth reconstruction for autonomous driving by introducing a method that uses LiDAR point-clouds and RGB images, resulting in improved depth estimation with a new edge-preserving smooth loss function.
3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot perception, and to that end, we introduce a method for jointly training 3D object detection and monocular dense depth reconstruction neural networks. It takes as inputs, a LiDAR point-cloud, and a single RGB image during inference and produces object pose predictions as well as a densely reconstructed depth map. LiDAR point-cloud is converted into a set of voxels, and its features are extracted using 3D convolution layers, from which we regress object pose parameters. Corresponding RGB image features are extracted using another 2D convolutional neural network. We further use these combined features to predict a dense depth map. While our object detection is trained in a supervised manner, the depth prediction network is trained with both self-supervised and supervised loss functions. We also introduce a loss function, edge-preserving smooth loss, and show that this results in better depth estimation compared to the edge-aware smooth loss function, frequently used in depth prediction works.