Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints
We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a least squares solution for the inverse 2D to 3D geometric mapping problem, using the camera projection matrix. The closed-form solution of the mathematical system, along with the initial output of the adapted Faster R-CNN are then passed through a final ShiftNet network that refines the result using our newly proposed Volume Displacement Loss. Our novel, geometrically constrained deep learning approach to monocular 3D object detection obtains top results on KITTI 3D Object Detection Benchmark, being the best among all monocular methods that do not use any pre-trained network for depth estimation.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionDeep LearningDepth EstimationFormMonocular 3D Object DetectionObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
Monocular 3D object detection is valuable for various applications such as robotics and AR/VR. Existing methods are confined to closed-set settings, where the training and testing sets consist of the same scenes and/or o…
Monocular 3D Object DetectionGrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
Modern 3D object detectors have immensely benefited from the end-to-end learning idea. However, most of them use a post-processing algorithm called Non-Maximal Suppression (NMS) only during inference. While there were at…
2D Object Detection3D Object Detection3D Object Detection From Monocular ImagesMonocular 3D Object Detection+3Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting
As cameras are increasingly deployed in new application domains such as autonomous driving, performing 3D object detection on monocular images becomes an important task for visual scene understanding. Recent advances on …
3D Object DetectionAutonomous DrivingDepth EstimationMonocular 3D Object Detection+5MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection
Monocular temporal 3D detection aims to detect objects in 3D, given a monocular video. Query-based 3D detectors unify detection and cross-view association, but their learnable queries fit the spatial distribution of the …
Domain Generalization3D Object DetectionViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts
Monocular depth estimation is a critical task for autonomous driving and many other computer vision applications. While significant progress has been made in this field, the effects of viewpoint shifts on depth estimatio…
Autonomous DrivingDepth EstimationHomography EstimationMonocular Depth Estimation+2