OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection

by   Yongzhi Su, et al.

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.


page 1

page 4

page 7


Object-Aware Centroid Voting for Monocular 3D Object Detection

Monocular 3D object detection aims to detect objects in a 3D physical wo...

Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels

The training of deep-learning-based 3D object detectors requires large d...

Sequential Decision-Making for Active Object Detection from Hand

A key component of understanding hand-object interactions is the ability...

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

Monocular 3D object detection aims to localize 3D bounding boxes in an i...

Visible Feature Guidance for Crowd Pedestrian Detection

Heavy occlusion and dense gathering in crowd scene make pedestrian detec...

BBBD: Bounding Box Based Detector for Occlusion Detection and Order Recovery

Occlusion handling is one of the challenges of object detection and segm...

Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection

The ground plane prior is a very informative geometry clue in monocular ...

Please sign up or login with your details

Forgot password? Click here to reset