Related papers: Pre-training with 3D Synthetic Data: Learning 3D P…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots. Certain existing studies have split input point clouds into small regions such as 1m x 1m; one…

Object pose estimation from a single view remains a challenging problem. In particular, partial observability, occlusions, and object symmetries eventually result in pose ambiguity. To account for this multimodality, this work proposes…

3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and…

Learning local descriptors is an important problem in computer vision. While there are many techniques for learning local patch descriptors for 2D images, recently efforts have been made for learning local descriptors for 3D points. The…

We propose a method to generate 3D shapes using point clouds. Given a point-cloud representation of a 3D shape, our method builds a kd-tree to spatially partition the points. This orders them consistently across all shapes, resulting in…

3D scene understanding has become an essential area of research with applications in autonomous driving, robotics, and augmented reality. Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful approach, combining explicit modeling…

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…

Semantic segmentation of 3D point cloud data often comes with high annotation costs. Active learning automates the process of selecting which data to annotate, reducing the total amount of annotation needed to achieve satisfactory…

Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models. However, learning from synthetic data may not generalize to…

Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional…

Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from…

Pre-training is crucial in 3D-related fields such as autonomous driving where point cloud annotation is costly and challenging. Many recent studies on point cloud pre-training, however, have overlooked the issue of incompleteness, where…

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…

Pre-trained 3D vision models have gained significant attention for their promising performance on point cloud data. However, fully fine-tuning these models for downstream tasks is computationally expensive and storage-intensive. Existing…

Instance segmentation of point clouds is a crucial task in 3D field with numerous applications that involve localizing and segmenting objects in a scene. However, achieving satisfactory results requires a large number of manual annotations,…

Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement,…

Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…

High quality upsampling of sparse 3D point clouds is critically useful for a wide range of geometric operations such as reconstruction, rendering, meshing, and analysis. In this paper, we propose a data-driven algorithm that enables an…

Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this,…