paper-with-me

홈 › Papers

Dense RepPoints: Representing Visual Objects with Dense Point Sets

2019-12-24 · ECCV 2020 8 · Ze Yang, Yinghao Xu, Han Xue, Zheng Zhang, Raquel Urtasun, Li-Wei Wang, Stephen Lin, Han Hu

We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level. Techniques are proposed to efficiently process these dense points, maintaining near-constant complexity with increasing point numbers. Dense RepPoints is shown to represent and learn object segments well, with the use of a novel distance transform sampling method combined with set-to-set supervision. The distance transform sampling combines the strengths of contour and grid representations, leading to performance that surpasses counterparts based on contours or grids. Code is available at \url{https://github.com/justimyhxu/Dense-RepPoints}.

📄 PDF Abstract BibTeX arXiv:1912.11473

Code (2)

justimyhxu/Dense-RepPoints 공식 구현 pytorch
Scalsol/RepPointsV2 pytorch

Tasks

ObjectObject Detection

Methods 이 논문이 사용한 방법론

RepPoints RepPoints is a representation for object detection that consists of a set of points which indicate the spatial extent of an object and semantically significant local areas.…

Similar Papers 제목 키워드 기반

RepPoints: Point Set Representation for Object Detection

2019-04-25 · ICCV 2019 10 · Ze Yang, Shaohui Liu, Han Hu, Li-Wei Wang 외

Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but prov…

Objectobject-detectionObject Detection

Category-level Shape Estimation for Densely Cluttered Objects

2023-02-23 · Zhenyu Wu, Ziwei Wang, Jiwen Lu, Haibin Yan

Accurately estimating the shape of objects in dense clutters makes important contribution to robotic packing, because the optimal object arrangement requires the robot planner to acquire shape information of all existed …

Instance SegmentationObjectPoint cloud reconstructionSegmentation+1

Continuous Surface Embeddings

2020-11-24 · NeurIPS 2020 12 · Natalia Neverova, David Novotny, Vasil Khalidov, Marc Szafraniec 외

In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific …

Animal Pose EstimationPose Estimation

RepPoints V2: Verification Meets Regression for Object Detection

2020-07-16 · NeurIPS 2020 12 · Yihong Chen, Zheng Zhang, Yue Cao, Li-Wei Wang 외

Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to …

Instance SegmentationObjectobject-detectionObject Detection+4

DOMR: Establishing Cross-View Segmentation via Dense Object Matching

2025-08-06 · Jitong Liao, Yulu Gao, Shaofei Huang, Jialin Gao 외 arxiv

Cross-view object correspondence involves matching objects between egocentric (first-person) and exocentric (third-person) views. It is a critical yet challenging task for visual understanding. In this work, we propose t…