Related papers: Diffusion-Driven Inter-Outer Surface Separation fo…

Point clouds are crucial for capturing three-dimensional data but often suffer from incompleteness due to limitations such as resolution and occlusion. Traditional methods typically rely on point-based approaches within discriminative…

Point clouds are widely used for infrastructure monitoring by providing geometric information, where segmentation is required for downstream tasks such as defect detection. Existing research has automated semantic segmentation of structural…

In this work, we investigate an original strategy in order to derive a statistical modeling of the interface in gas-liquid two-phase flows through geometrical variables. The con- tribution is two-fold. First it participates in the…

Multi-label classification has broad applications and depends on powerful representations capable of capturing multi-label interactions. We introduce \textit{Diff-Feat}, a simple but powerful framework that extracts intermediate features…

This paper presents a new method, Diffusing Winding Gradients (DWG), for reconstructing watertight 3D surfaces from unoriented point clouds. Our method exploits the alignment between the gradients of the generalized winding number (GWN)…

Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails…

The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset.…

In turbid media, scattering of light scrambles information of the incident beam and represents an obstacle to optical imaging. Noninvasive imaging through opaque layers is challenging for dynamic and wide-field objects due to unreliable…

We present a novel and flexible architecture for point cloud segmentation with dual-representation iterative learning. In point cloud processing, different representations have their own pros and cons. Thus, finding suitable ways to…

Existing deep learning based methods effectively prompt the performance of aerial scene classification. However, due to the large amount of parameters and computational cost, it is rather difficult to apply these methods to multiple…

This study introduces a novel point-wise diffusion model that processes spatio-temporal points independently to efficiently predict complex physical systems with shape variations. This methodological contribution lies in applying forward…

Many particle physics datasets like those generated at colliders are described by continuous coordinates (in contrast to grid points like in an image), respect a number of symmetries (like permutation invariance), and have a stochastic…

We address the problem of data augmentation in a rotating turbulence set-up, a paradigmatic challenge in geophysical applications. The goal is to reconstruct information in two-dimensional (2D) cuts of the three-dimensional flow fields,…

Segmentation of brain structures from MRI is crucial for evaluating brain morphology, yet existing CNN and transformer-based methods struggle to delineate complex structures accurately. While current diffusion models have shown promise in…

In this paper, we propose a new method, called DoubleCoverUDF, for extracting the zero level-set from unsigned distance fields (UDFs). DoubleCoverUDF takes a learned UDF and a user-specified parameter $r$ (a small positive real number) as…

Generative diffusion models have shown empirical successes in point cloud resampling, generating a denser and more uniform distribution of points from sparse or noisy 3D point clouds by progressively refining noise into structure. However,…

We propose a novel variational approach for computing neural Signed Distance Fields (SDF) from unoriented point clouds. To this end, we replace the commonly used eikonal equation with the heat method, carrying over to the neural domain what…

Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great significance to autonomous driving. Most existing 3D reconstruction methods cannot be directly applied to this problem because they are elaborately designed…

We propose a method, named DualMesh-UDF, to extract a surface from unsigned distance functions (UDFs), encoded by neural networks, or neural UDFs. Neural UDFs are becoming increasingly popular for surface representation because of their…

The lack of spatial dimensional information remains a challenge in normal estimation from a single image. Recent diffusion-based methods have demonstrated significant potential in 2D-to-3D implicit mapping, they rely on data-driven…