paper-with-me

홈 › Papers

3D Object Detection With Latent Support Surfaces

2018-06-01 · CVPR 2018 6 · Zhile Ren, Erik B. Sudderth

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionObjectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts

2019-06-11 · Zhile Ren, Erik B. Sudderth

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+1

SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects

2023-11-11 · Peng Wang, Haiming Yao, Wenyong Yu

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 Learning

Towards Reflected Object Detection: A Benchmark

2024-07-08 · Zhongtian Wang, You Wu, Hui Zhou, Shuiwang Li

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 Detection

RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

2020-11-30 · CVPR 2021 1 · Yinyu Nie, Ji Hou, Xiaoguang Han, Matthias Nießner

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+3

Uni-Fusion: Universal Continuous Mapping

2023-03-22 · Yijun Yuan, Andreas Nuechter

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