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 …

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 …

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 …

Abstract Weakly Supervised Semantic Segmentation (WSSS) aims to learn the concept of
segmentation using image-level class labels. Recent WSSS works have shown promising …

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 …

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 …

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 …

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 …

Despite alleviating the dependence on dense annotations inherent to fully supervised
methods, weakly supervised point cloud semantic segmentation suffers from inadequate …

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 …