Related papers: CrossGen: Learning and Generating Cross Fields for…

Hexahedral meshes are widely used in simulation pipelines, yet automatic generation remains challenging for complex CAD geometries. Polycube-based hexahedral meshing is a representative approach due to its regular, parameterization-friendly…

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This…

Large-scale and diverse datasets are vital for training robust robotic manipulation policies, yet existing data collection methods struggle to balance scale, diversity, and quality. Simulation offers scalability but suffers from sim-to-real…

Existing psychophysical studies have revealed that the cross-modal visual-tactile perception is common for humans performing daily activities. However, it is still challenging to build the algorithmic mapping from one modality space to…

While high-quality texture maps are essential for realistic 3D asset rendering, few studies have explored learning directly in the texture space, especially on large-scale datasets. In this work, we depart from the conventional approach of…

Boundary representation (B-rep) of geometric models is a fundamental format in Computer-Aided Design (CAD). However, automatically generating valid and high-quality B-rep models remains challenging due to the complex interdependence between…

With the growth of 3D applications and the rapid increase in sensor-collected 3D point cloud data, there is a rising demand for efficient compression algorithms. Most existing learning-based compression methods handle geometry and color…

Multilayer networks allow one to represent diverse and coupled connectivity patterns --- e.g., time-dependence, multiple subsystems, or both --- that arise in many applications and which are difficult or awkward to incorporate into standard…

Accelerating the deep learning inference is very important for real-time applications. In this paper, we propose a novel method to fuse the layers of convolutional neural networks (CNNs) on Graphics Processing Units (GPUs), which applies…

Geometric representation-conditioned molecule generation provides an effective paradigm that decouples molecule representation modeling from structure generation. By decoupling molecule generation into two stages-first generating a…

Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this…

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 this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple…

Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representa tions offer complementary advantages for graphics applica tions. However, due to differences in representation and ren dering…

We present a CUDA accelerated implementation of the Characteristic/Scan Conversion algorithm to generate narrow band signed distance fields in logically Cartesian grids. We outline an approach of task and data management on GPUs based on an…

Molecular conformer generation (MCG) is an important task in cheminformatics and drug discovery. The ability to efficiently generate low-energy 3D structures can avoid expensive quantum mechanical simulations, leading to accelerated virtual…

Unified multimodal generative models aim to integrate image understanding and generation abilities, offering significant advantages in harnessing multimodal corpora, particularly interleaved text-image data. However, existing unified models…

Feature generation aims to generate new and meaningful features to create a discriminative representation space.A generated feature is meaningful when the generated feature is from a feature pair with inherent feature interaction. In the…

Inspired by generative paradigms in image and video, 3D shape generation has made notable progress, enabling the rapid synthesis of high-fidelity 3D assets from a single image. However, current methods still face challenges, including the…

We present MRGAN, a multi-rooted adversarial network which generates part-disentangled 3D point-cloud shapes without part-based shape supervision. The network fuses multiple branches of tree-structured graph convolution layers which produce…