2D-3D interlaced transformer for point cloud segmentation with scene-level supervision
Abstract We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and
3D data for weakly supervised point cloud segmentation. Research studies have shown that …
3D data for weakly supervised point cloud segmentation. Research studies have shown that …
All points matter: entropy-regularized distribution alignment for weakly-supervised 3D segmentation
Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where
only sparse ground-truth labels are available for learning. Existing methods often rely on …
only sparse ground-truth labels are available for learning. Existing methods often rely on …
A survey on weakly supervised 3D point cloud semantic segmentation
J Wang, Y Liu, H Tan, M Zhang - IET Computer Vision, 2024 - Wiley Online Library
With the popularity and advancement of 3D point cloud data acquisition technologies and
sensors, research into 3D point clouds has made considerable strides based on deep …
sensors, research into 3D point clouds has made considerable strides based on deep …
From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation
Abstract Weakly Supervised Semantic Segmentation (WSSS) aims to learn the concept of
segmentation using image-level class labels. Recent WSSS works have shown promising …
segmentation using image-level class labels. Recent WSSS works have shown promising …
Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle
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 …
While weakly supervised point cloud semantic segmentation (WSPCSS) with sparse …
A review of point cloud segmentation for understanding 3D indoor scenes
Y Sun, X Zhang, Y Miao - Visual Intelligence, 2024 - Springer
Point cloud segmentation is an essential task in three-dimensional (3D) vision and
intelligence. It is a critical step in understanding 3D scenes with a variety of applications …
intelligence. It is a critical step in understanding 3D scenes with a variety of applications …
3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance
In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic
Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model …
Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model …
Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignment
Label-efficient segmentation aims to perform effective segmentation on input data using only
sparse and limited ground-truth labels for training. This topic is widely studied in 3D point …
sparse and limited ground-truth labels for training. This topic is widely studied in 3D point …
Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
Despite alleviating the dependence on dense annotations inherent to fully supervised
methods, weakly supervised point cloud semantic segmentation suffers from inadequate …
methods, weakly supervised point cloud semantic segmentation suffers from inadequate …
You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding
3D scene understanding, eg, point cloud semantic and instance segmentation, often
requires large-scale annotated training data, but clearly, point-wise labels are too tedious to …
requires large-scale annotated training data, but clearly, point-wise labels are too tedious to …