paper-with-me

Papers Semantic Segmentation on ScanNet

“Semantic Segmentation on ScanNet” 태그가 달린 논문 5편 · 필터 해제

Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting

2024-03-22 · Jun Guo, Xiaojian Ma, Yue Fan, Huaping Liu 외

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods…

Instance SegmentationObject LocalizationScene UnderstandingSegmentation+2

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

2023-03-24 · CVPR 2023 1 · Xiaoyang Wu, Xin Wen, Xihui Liu, Hengshuang Zhao

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend …

Contrastive LearningData AugmentationRepresentation LearningSemantic Segmentation+1

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

2022-10-11 · Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu 외

As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations …

3D Point Cloud Classification3D Semantic SegmentationLIDAR Semantic SegmentationPoint Cloud Classification+4

Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

2022-04-19 · Chun-Yu Sun, Yu-Qi Yang, Hao-Xiang Guo, Peng-Shuai Wang 외

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few la…

SegmentationSemantic SegmentationSemantic Segmentation on ScanNetUnsupervised Pre-training

Bidirectional Projection Network for Cross Dimension Scene Understanding

2021-03-26 · CVPR 2021 1 · WenBo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia 외

2D image representations are in regular grids and can be processed efficiently, whereas 3D point clouds are unordered and scattered in 3D space. The information inside these two visual domains is well complementary, e.g.…

2D Semantic Segmentation3D Semantic SegmentationScene RecognitionScene Understanding+2
1–5 / 5