Related papers: C-GenReg: Training-Free 3D Point Cloud Registratio…

Diffusion models have shown the great potential in the point cloud registration (PCR) task, especially for enhancing the robustness to challenging cases. However, existing diffusion-based PCR methods primarily focus on instance-level…

Point cloud registration for 3D objects is a challenging task due to sparse and noisy measurements, incomplete observations and large transformations. In this work, we propose \textbf{G}raph \textbf{M}atching \textbf{C}onsensus…

Cross-modal data registration has long been a critical task in computer vision, with extensive applications in autonomous driving and robotics. Accurate and robust registration methods are essential for aligning data from different…

Point cloud registration is a key task in many computational fields. Previous correspondence matching based methods require the inputs to have distinctive geometric structures to fit a 3D rigid transformation according to point-wise sparse…

Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial…

We address the challenge of point cloud registration using color information, where traditional methods relying solely on geometric features often struggle in low-overlap and incomplete scenarios. To overcome these limitations, we propose…

Point cloud registration aims to provide estimated transformations to align point clouds, which plays a crucial role in pose estimation of various navigation systems, such as surgical guidance systems and autonomous vehicles. Despite the…

Generating a 3D point cloud from a single 2D image is of great importance for 3D scene understanding applications. To reconstruct the whole 3D shape of the object shown in the image, the existing deep learning based approaches use either…

This study introduces a novel framework, G3Reg, for fast and robust global registration of LiDAR point clouds. In contrast to conventional complex keypoints and descriptors, we extract fundamental geometric primitives, including planes,…

Some deep learning-based point cloud registration methods struggle with zero-shot generalization, often requiring dataset-specific hyperparameter tuning or retraining for new environments. We identify three critical limitations: (a) fixed…

3D generative modeling is accelerating as the technology allowing the capture of geometric data is developing. However, the acquired data is often inconsistent, resulting in unregistered meshes or point clouds. Many generative learning…

We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-latent diffusion to the radar domain by representing radar measurements in…

In this paper, we present a novel registration framework, HumanReg, that learns a non-rigid transformation between two human point clouds end-to-end. We introduce body prior into the registration process to efficiently handle this type of…

Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial distribution of objects, environment and agent itself. To…

Scanning real-life scenes with modern registration devices typically gives incomplete point cloud representations, primarily due to the limitations of partial scanning, 3D occlusions, and dynamic light conditions. Recent works on processing…

Recent success of vision foundation models have shown promising performance for the 2D perception tasks. However, it is difficult to train a 3D foundation network directly due to the limited dataset and it remains under explored whether…

We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences. The advantage of the feature-metric projection…

3D point cloud generation by the deep neural network from a single image has been attracting more and more researchers' attention. However, recently-proposed methods require the objects be captured with relatively clean backgrounds, fixed…

Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration. This paper proposes a learning framework COTReg by jointly considering the pointwise and structural matchings to…

Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global…