VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This appealing ability is vital for recognition and understanding. To enable such capability in AI systems, we propose VoxFormer, a Transformer-based semantic scene completion framework that can output complete 3D volumetric semantics from only 2D images. Our framework adopts a two-stage design where we start from a sparse set of visible and occupied voxel queries from depth estimation, followed by a densification stage that generates dense 3D voxels from the sparse ones. A key idea of this design is that the visual features on 2D images correspond only to the visible scene structures rather than the occluded or empty spaces. Therefore, starting with the featurization and prediction of the visible structures is more reliable. Once we obtain the set of sparse queries, we apply a masked autoencoder design to propagate the information to all the voxels by self-attention. Experiments on SemanticKITTI show that VoxFormer outperforms the state of the art with a relative improvement of 20.0% in geometry and 18.1% in semantics and reduces GPU memory during training to less than 16GB. Our code is available on https://github.com/NVlabs/VoxFormer.
Code (1)
Tasks
3D geometry3D Semantic Scene Completion3D Semantic Scene Completion from a single RGB imageDepth EstimationGPUSimilar Papers 제목 키워드 기반
SparseVoxFormer: Sparse Voxel-based Transformer for Multi-modal 3D Object Detection
Most previous 3D object detection methods that leverage the multi-modality of LiDAR and cameras utilize the Bird's Eye View (BEV) space for intermediate feature representation. However, this space uses a low x, y-resolut…
3D Object Detectionobject-detectionObject DetectionSnakeVoxFormer: Transformer-based Single Image\\Voxel Reconstruction with Run Length Encoding
Deep learning-based 3D object reconstruction has achieved unprecedented results. Among those, the transformer deep neural model showed outstanding performance in many applications of computer vision. We introduce SnakeVo…
3D Object ReconstructionData CompressionObject ReconstructionCamera-based 3D Semantic Scene Completion with Sparse Guidance Network
Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies…
3D Semantic Scene CompletionAutonomous DrivingDepth EstimationDepth PredictionMulti-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completion
Camera-based 3D semantic scene completion (SSC) offers a cost-effective solution for assessing the geometric occupancy and semantic labels of each voxel in the surrounding 3D scene with image inputs, providing a voxel-le…
3D Semantic Scene CompletionAutonomous DrivingSpiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras
We propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous and spatially sparse events, our goal is to discover an event representa…
Gesture RecognitionEvent-based visionObject Detection