Related papers: EipFormer: Emphasizing Instance Positions in 3D In…

Most existing methods realize 3D instance segmentation by extending those models used for 3D object detection or 3D semantic segmentation. However, these non-straightforward methods suffer from two drawbacks: 1) Imprecise bounding boxes or…

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is…

Most existing 3D instance segmentation methods are derived from 3D semantic segmentation models. However, these indirect approaches suffer from certain limitations. They fail to fully leverage global and local semantic information for…

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object…

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and IoU scores to select the top prediction as…

DEtection TRansformer (DETR) started a trend that uses a group of learnable queries for unified visual perception. This work begins by applying this appealing paradigm to LiDAR-based point cloud segmentation and obtains a simple yet…

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we…

Separating 3D point clouds into individual instances is an important task for 3D vision. It is challenging due to the unknown and varying number of instances in a scene. Existing deep learning based works focus on a two-step pipeline: first…

Interactive point cloud segmentation has become a pivotal task for understanding 3D scenes, enabling users to guide segmentation models with simple interactions such as clicks, therefore significantly reducing the effort required to tailor…

In recent years, transformer-based models have exhibited considerable potential in point cloud instance segmentation. Despite the promising performance achieved by existing methods, they encounter challenges such as instance query…

While recent feed-forward 3D reconstruction models provide a strong geometric foundation for scene understanding, extending them to 3D instance segmentation typically relies on a disjointed "lift-and-cluster" paradigm. Grouping dense…

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple…

In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not…

3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to…

The transformation of features from 2D perspective space to 3D space is essential to multi-view 3D object detection. Recent approaches mainly focus on the design of view transformation, either pixel-wisely lifting perspective view features…

This paper introduces a new problem in 3D point cloud: few-shot instance segmentation. Given a few annotated point clouds exemplified a target class, our goal is to segment all instances of this target class in a query point cloud. This…

Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further…

Instance 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…

Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories…

Transformers have been seldom employed in point cloud roof plane instance segmentation, which is the focus of this study, and existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints. To…