Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes From 2D Ones in RGB-Depth Images
This paper addresses the problem of amodal perception of 3D object detection. The task is to not only find object localizations in the 3D world, but also estimate their physical sizes and poses, even if only parts of them are visible in the RGB-D image. Recent approaches have attempted to harness point cloud from depth channel to exploit 3D features directly in the 3D space and demonstrated the superiority over traditional 2.5D representation approaches. We revisit the amodal 3D detection problem by sticking to the 2.5D representation framework, and directly relate 2.5D visual appearance to 3D objects. We propose a novel 3D object detection system that simultaneously predicts objects' 3D locations, physical sizes, and orientations in indoor scenes. Experiments on the NYUV2 dataset show our algorithm significantly outperforms the state-of-the-art and indicates 2.5D representation is capable of encoding features for 3D amodal object detection. All source code and data is on https://github.com/phoenixnn/Amodal3Det.
Code (1)
Tasks
3D Object DetectionObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
We focus on the task of amodal 3D object detection in RGB-D images, which aims to produce a 3D bounding box of an object in metric form at its full extent. We introduce Deep Sliding Shapes, a 3D ConvNet formulation that …
3D Object DetectionObjectobject-detectionObject Detection+2TAO-Amodal: A Benchmark for Tracking Any Object Amodally
Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants. Its significance extends to applications like autonomous driving, where a clear u…
Amodal TrackingAutonomous DrivingBenchmarkingData Augmentation+1Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes
Object detection is an important task in environment perception for autonomous driving. Modern 2D object detection frameworks such as Yolo, SSD or Faster R-CNN predict multiple bounding boxes per object that are refined …
2D Object DetectionAutonomous DrivingObjectobject-detection+1Amodal Intra-class Instance Segmentation: Synthetic Datasets and Benchmark
Images of realistic scenes often contain intra-class objects that are heavily occluded from each other, making the amodal perception task that requires parsing the occluded parts of the objects challenging. Although impo…
Amodal Instance SegmentationInstance SegmentationRobotic GraspingSemantic SegmentationAmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving
Unlike humans, who can effortlessly estimate the entirety of objects even when partially occluded, modern computer vision algorithms still find this aspect extremely challenging. Leveraging this amodal perception for aut…
Autonomous DrivingBenchmarkingDepth EstimationScene Understanding