Related papers: Learning Gradient Fields for Shape Generation

With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision. However, in 3D vision, the over-reliance on…

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…

Driven by the increasing demand for accurate and efficient representation of 3D data in various domains, point cloud sampling has emerged as a pivotal research topic in 3D computer vision. Recently, learning-to-sample methods have garnered…

Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…

This work introduces a new task of instance-incremental scene graph generation: Given a scene of the point cloud, representing it as a graph and automatically increasing novel instances. A graph denoting the object layout of the scene is…

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few…

Point cloud upsampling focuses on generating a dense, uniform and proximity-to-surface point set. Most previous approaches accomplish these objectives by carefully designing a single-stage network, which makes it still challenging to…

In the recent years, the research community has witnessed growing use of 3D point cloud data for the high applicability in various real-world applications. By means of 3D point cloud, this modality enables to consider the actual size and…

In recent years, point cloud generation has gained significant attention in 3D generative modeling. Among existing approaches, point-based methods directly generate point clouds without relying on other representations such as latent…

Mesh generation is of great value in various applications involving computer graphics and virtual content, yet designing generative models for meshes is challenging due to their irregular data structure and inconsistent topology of meshes…

We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike most existing models that learn to deterministically translate a latent vector to a shape, our model, Point-Voxel Diffusion (PVD), is a unified,…

Pre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains. However, due to the unordered and non-uniform density characteristics of point clouds, it is non-trivial…

The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry…

We introduce a diffusion-based generative model to describe the distribution of galaxies in our Universe directly as a collection of points in 3-D space (coordinates) optionally with associated attributes (e.g., velocities and masses),…

In this paper, we propose Neural Points, a novel point cloud representation and apply it to the arbitrary-factored upsampling task. Different from traditional point cloud representation where each point only represents a position or a local…

Generating realistic 3D point clouds is a fundamental problem in computer vision with applications in remote sensing, robotics, and digital object modeling. Existing generative approaches primarily capture geometry, and when semantics are…

Processing 3D pointclouds with Deep Learning methods is not an easy task. A common choice is to do so with Graph Neural Networks, but this framework involves the creation of edges between points, which are explicitly not related between…

Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, we present a novel deep learning-based model,…

We present a novel deep learning framework for flow field predictions in irregular domains when the solution is a function of the geometry of either the domain or objects inside the domain. Grid vertices in a computational fluid dynamics…

Fast and accurate 3D shape generation from point clouds is essential for applications in robotics, AR/VR, and digital content creation. We introduce ConTiCoM-3D, a continuous-time consistency model that synthesizes 3D shapes directly in…