3D Object Detection With Latent Support Surfaces
We develop a 3D object detection algorithm that uses latent support surfaces to capture contextual relationships in indoor scenes. Existing 3D representations for RGB-D images capture the local shape and appearance of object categories, but have limited power to represent objects with different visual styles. The detection of small objects is also challenging because the search space is very large in 3D scenes. However, we observe that much of the shape variation within 3D object categories can be explained by the location of a latent support surface, and smaller objects are often supported by larger objects. Therefore, we explicitly use latent support surfaces to better represent the 3D appearance of large objects, and provide contextual cues to improve the detection of small objects. We evaluate our model with 19 object categories from the SUN RGB-D database, and demonstrate state-of-the-art performance.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts
We develop new representations and algorithms for three-dimensional (3D) object detection and spatial layout prediction in cluttered indoor scenes. We first propose a clouds of oriented gradient (COG) descriptor that lin…
3D Object DetectionGeneral Classificationobject-detectionObject Detection+1SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects
The unsupervised visual inspection of defects in industrial products poses a significant challenge due to substantial variations in product surfaces. Current unsupervised models struggle to strike a balance between detec…
Anomaly DetectionSelf-Supervised LearningTowards Reflected Object Detection: A Benchmark
Object detection has greatly improved over the past decade thanks to advances in deep learning and large-scale datasets. However, detecting objects reflected in surfaces remains an underexplored area. Reflective surfaces…
Objectobject-detectionObject DetectionRfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
Semantic scene understanding from point clouds is particularly challenging as the points reflect only a sparse set of the underlying 3D geometry. Previous works often convert point cloud into regular grids (e.g. voxels o…
3D geometryObjectobject-detectionObject Detection+3Uni-Fusion: Universal Continuous Mapping
We present Uni-Fusion, a universal continuous mapping framework for surfaces, surface properties (color, infrared, etc.) and more (latent features in CLIP embedding space, etc.). We propose the first universal implicit e…
Scene Understanding