3D point clouds/Segmentation11 [논문리뷰]MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation Paper OverviewACM MM'24https://arxiv.org/abs/2411.01781 MSTA3D: Multi-scale Twin-attention for 3D Instance SegmentationRecently, transformer-based techniques incorporating superpoints have become prevalent in 3D instance segmentation. However, they often encounter an over-segmentation problem, especially noticeable with large objects. Additionally, unreliable mask predictiarxiv.orgAbstract본 논문은 .. 2025. 3. 24. [논문리뷰]PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation Paper OverviewCVPR'20https://arxiv.org/abs/2004.01658 PointGroup: Dual-Set Point Grouping for 3D Instance SegmentationInstance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this paper, we present PointGroup, a new end-to-end bottom-up architecture, specarxiv.orgAbstract본 논문은 새.. 2025. 3. 19. [논문리뷰]3D Compositional Zero-shot Learning with DeCompositional Consensus 이 논문은 3D point clouds part segmentation에서 compositional zero-shot learning을 수행하는 논문이다. 본 논문의 큰 기조는 object에서 part를 구한 뒤 part정보들로 부터 classification을 수행하는 것이다. ECCV'22 https://arxiv.org/abs/2111.14673 3D Compositional Zero-shot Learning with DeCompositional Consensus Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be co.. 2023. 11. 21. [논문리뷰] Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training 이 논문은 3D segmentation을 학습시킬 때 다양한 dataset을 사용하기 위한 방법으로 prompt tuning 방법론을 제안한다. (최근 대회를 연속 2개를 나가서 논문을 한참 못읽었다..) arXiv'23 https://arxiv.org/abs/2308.09718 Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not ye.. 2023. 10. 16. Point Transformer 리뷰 해당 논문은 point cloud에 transformer를 적용한 논문이다. 해당 논문을 읽어보면 transformer 특성이 point cloud를 처리하기에 알맞다는 것을 알 수 있다. ICCV' 21 https://arxiv.org/abs/2012.09164 Point Transformer Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Inspired by this success, we investigate the applic.. 2023. 8. 9. [논문리뷰] 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks 이 논문은 앞서 포스팅한 3D semantic segmentation의 discretization-based methods의 Sparse Discretization Representation 범주에 들어가는 논문이다. CVPR'18 https://arxiv.org/abs/1711.10275 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally de.. 2023. 7. 20. 이전 1 2 다음
