Related papers: UTOPIC: Uncertainty-aware Overlap Prediction Netwo…

Recent advancements in Diffusion Transformer (DiT) models have significantly improved 3D point cloud generation. However, existing methods primarily focus on local feature extraction while overlooking global topological information, such as…

Point cloud registration is a prerequisite for many applications in computer vision and robotics. Most existing methods focus on pairwise registration of two point clouds with high overlap. Although there have been some methods for low…

Accurate skin lesion segmentation is vital for dermoscopic Computer-Aided Diagnosis. However, visual ambiguity and morphological irregularity often defeat spatial modeling, necessitating multi-domain architectures. Existing paradigms…

In healthcare, accurately classifying medical images is vital, but conventional methods often hinge on medical data with a consistent grid structure, which may restrict their overall performance. Recent medical research has been focused on…

Modeling object dynamics with a neural network is an important problem with numerous applications. Most recent work has been based on graph neural networks. However, physics happens in 3D space, where geometric information potentially plays…

Over-the-air computation (AirComp) has emerged as a promising technology that enables simultaneous transmission and computation through wireless channels. In this paper, we investigate the networked AirComp in multiple clusters allowing…

Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by…

Learning a medical image segmentation model is an inherently ambiguous task, as uncertainties exist in both images (noise) and manual annotations (human errors and bias) used for model training. To build a trustworthy image segmentation…

Point cloud registration is a task to estimate the rigid transformation between two unaligned scans, which plays an important role in many computer vision applications. Previous learning-based works commonly focus on supervised…

Encoder-Decoder networks such as U-Nets have been applied successfully in a wide range of computer vision tasks, especially for image segmentation of different flavours across different fields. Nevertheless, most applications lack of a…

This work presents a novel method for fitting superquadrics to point clouds under the contamination of noise and outliers, which has many applications for shape modeling across diverse fields. Unlike prior approaches that either exclusively…

This work investigates the use of robust optimal transport (OT) for shape matching. Specifically, we show that recent OT solvers improve both optimization-based and deep learning methods for point cloud registration, boosting accuracy at an…

Clouds classification is a great challenge in meteorological research. The different types of clouds, currently known and present in our skies, can produce radioactive effects that impact on the variation of atmospheric conditions, with the…

Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications. In this work, we propose Point Completion Network (PCN), a novel…

We introduce Rectified Point Flow, a unified parameterization that formulates pairwise point cloud registration and multi-part shape assembly as a single conditional generative problem. Given unposed point clouds, our method learns a…

Point cloud registration (PCR) is an essential task in 3D vision. Existing methods achieve increasingly higher accuracy. However, a large proportion of non-overlapping points in point cloud registration consume a lot of computational…

Image-to-point-cloud registration (I2P) is a fundamental task in robotic applications such as manipulation,grasping, and localization. Existing deep learning-based I2P methods seek to align image and point cloud features in a learned…

Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically…

We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes. The key characteristics are the following techniques that exploit 3D positional knowledge for point cloud matching: 1) An…

Recent investigations on rotation invariance for 3D point clouds have been devoted to devising rotation-invariant feature descriptors or learning canonical spaces where objects are semantically aligned. Examinations of learning frameworks…