Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle

2024-01-01 · CVPR 2024 1 · Hyeokjun Kweon, Jihun Kim, Kuk-Jin Yoon

Manual annotation of every point in a point cloud is a costly and labor-intensive process. While weakly supervised point cloud semantic segmentation (WSPCSS) with sparse annotation shows promise the limited information from initial sparse labels can place an upper bound on performance. As a new research direction for WSPCSS we propose a novel Region Exploration via Artificial Labeling (REAL) framework. It leverages a foundational image model as an artificial oracle within the active learning context eliminating the need for manual annotation by a human oracle. To integrate the 2D model into the 3D domain we first introduce a Projection-based Point-toSegment (PP2S) module designed to enable prompt segmentation of 3D data without additional training. The REAL framework samples query points based on model predictions and requests annotations from PP2S dynamically refining labels and improving model training. Furthermore to overcome several challenges of employing an artificial model as an oracle we formulate effective query sampling and label updating strategies. Our comprehensive experiments and comparisons demonstrate that the REAL framework significantly outperforms existing methods across various benchmarks. The code is available at https://github.com/jihun1998/AO.

📄 PDF Abstract BibTeX

Code (1)

jihun1998/ao 공식 구현 pytorch

Tasks

Active Learning Semantic Segmentation

Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud

2022-12-09 · AAAI 2021 5 · Yachao Zhang, Zonghao Li, Yuan Xie, Yanyun Qu 외

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost…

Colorization Pseudo Label Self-Supervised Learning Semantic Segmentation+2

Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds

2021-07-23 · Jiacheng Wei, Guosheng Lin, Kim-Hui Yap, Fayao Liu 외

Semantic segmentation on 3D point clouds is an important task for 3D scene understanding. While dense labeling on 3D data is expensive and time-consuming, only a few works address weakly supervised semantic point cloud s…

Point Cloud Segmentation Scene Understanding Segmentation Semantic Segmentation+2

Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds

2020-03-29 · CVPR 2020 6 · Jiacheng Wei, Guosheng Lin, Kim-Hui Yap, Tzu-Yi Hung 외

Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, …

3D Semantic Segmentation Point Cloud Segmentation Scene Understanding Segmentation+1

Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

2023-12-27 · Xiawei Li, Qingyuan Xu, Jing Zhang, Tianyi Zhang 외

3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation pr…

3D Semantic Segmentation Point Cloud Segmentation Segmentation Semantic Segmentation

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

2022-07-19 · Zhonghua Wu, Yicheng Wu, Guosheng Lin, Jianfei Cai 외

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annota…

Point Cloud Segmentation Segmentation