SparseDet: Towards End-to-End 3D Object Detection
This work addresses the inefficiency and complexity of dense candidate methods in 3D object detection for applications like autonomous driving, though it appears incremental as it builds on transformer-based approaches.
The paper tackles the problem of 3D object detection from point clouds by proposing SparseDet, an end-to-end method that uses a fixed set of learnable proposals instead of dense candidates, achieving competitive accuracy with a speed of 34.5 FPS and eliminating post-processing steps like non-maximum suppression.
In this paper, we propose SparseDet for end-to-end 3D object detection from point cloud. Existing works on 3D object detection rely on dense object candidates over all locations in a 3D or 2D grid following the mainstream methods for object detection in 2D images. However, this dense paradigm requires expertise in data to fulfill the gap between label and detection. As a new detection paradigm, SparseDet maintains a fixed set of learnable proposals to represent latent candidates and directly perform classification and localization for 3D objects through stacked transformers. It demonstrates that effective 3D object detection can be achieved with none of post-processing such as redundant removal and non-maximum suppression. With a properly designed network, SparseDet achieves highly competitive detection accuracy while running with a more efficient speed of 34.5 FPS. We believe this end-to-end paradigm of SparseDet will inspire new thinking on the sparsity of 3D object detection.