paper-with-me

Papers

Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

2020-01-14 · Lulu Tang, Ke Chen, Chaozheng Wu, Yu Hong, Kui Jia, Zhi-Xin Yang

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing local surface manifolds embedded in 3D Euclidean space to discriminate semantic classes or object parts as additional supervision signals. This paper is the first attempt to propose a unique multi-task geometric learning network to improve semantic analysis by auxiliary geometric learning with local shape properties, which can be either generated via physical computation from point clouds themselves as self-supervision signals or provided as privileged information. Owing to explicitly encoding local shape manifolds in favor of semantic analysis, the proposed geometric self-supervised and privileged learning algorithms can achieve superior performance to their backbone baselines and other state-of-the-art methods, which are verified in the experiments on the popular benchmarks.

📄 PDF Abstract BibTeX arXiv:2001.04803

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Self-supervised Learning of Point Clouds via Orientation Estimation

2020-08-01 · Omid Poursaeed, Tianxing Jiang, Han Qiao, Nayun Xu 외

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, …

3D Point Cloud Linear ClassificationSelf-Supervised LearningUnsupervised 3D Point Cloud Linear Evaluation

SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds

2021-04-11 · Qingyong Hu, Bo Yang, Guangchi Fang, Yulan Guo 외

Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existi…

Semantic SegmentationSemantic SimilaritySemantic Textual SimilarityWeakly supervised Semantic Segmentation+1

Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision

2022-01-09 · Yan Liu, Qingyong Hu, Yinjie Lei, Kai Xu 외

Learning dense point-wise semantics from unstructured 3D point clouds with fewer labels, although a realistic problem, has been under-explored in literature. While existing weakly supervised methods can effectively learn…

Semantic Segmentation

Enhancing 3D LiDAR Segmentation by Shaping Dense and Accurate 2D Semantic Predictions

2026-02-21 · Xiaoyu Dong, Tiankui Xian, Wanshui Gan, Naoto Yokoya arxiv

Semantic segmentation of 3D LiDAR point clouds is important in urban remote sensing for understanding real-world street environments. This task, by projecting LiDAR point clouds and 3D semantic labels as sparse maps, can…

Semantic SegmentationPoint Clouds

Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes

2020-04-26 · Hai-Yan Wang, Xuejian Rong, Liang Yang, Jinglun Feng 외

The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a no…

3D Semantic SegmentationPoint Cloud SegmentationScene SegmentationSegmentation+3