OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection
This work addresses the challenge of robust 3D object detection from monocular images for applications like autonomous driving, representing an incremental improvement over existing two-stage methods.
The paper tackles the problem of monocular 3D object detection by proposing OPA-3D, a single-stage, end-to-end network that jointly estimates depth and object bounding boxes with occlusion-aware optimization, resulting in outperforming state-of-the-art methods on the Car category while maintaining real-time inference speed.
Despite monocular 3D object detection having recently made a significant leap forward thanks to the use of pre-trained depth estimators for pseudo-LiDAR recovery, such two-stage methods typically suffer from overfitting and are incapable of explicitly encapsulating the geometric relation between depth and object bounding box. To overcome this limitation, we instead propose OPA-3D, a single-stage, end-to-end, Occlusion-Aware Pixel-Wise Aggregation network that to jointly estimate dense scene depth with depth-bounding box residuals and object bounding boxes, allowing a two-stream detection of 3D objects, leading to significantly more robust detections. Thereby, the geometry stream denoted as the Geometry Stream, combines visible depth and depth-bounding box residuals to recover the object bounding box via explicit occlusion-aware optimization. In addition, a bounding box based geometry projection scheme is employed in an effort to enhance distance perception. The second stream, named as the Context Stream, directly regresses 3D object location and size. This novel two-stream representation further enables us to enforce cross-stream consistency terms which aligns the outputs of both streams, improving the overall performance. Extensive experiments on the public benchmark demonstrate that OPA-3D outperforms state-of-the-art methods on the main Car category, whilst keeping a real-time inference speed. We plan to release all codes and trained models soon.