Surface Geometry Processing: An Efficient Normal-based Detail
Representation
- URL: http://arxiv.org/abs/2307.07945v1
- Date: Sun, 16 Jul 2023 04:46:32 GMT
- Title: Surface Geometry Processing: An Efficient Normal-based Detail
Representation
- Authors: Wuyuan Xie, Miaohui Wang, Di Lin, Boxin Shi, and Jianmin Jiang
- Abstract summary: We introduce an efficient surface detail processing framework in 2D normal domain.
We show that the proposed normal-based representation has three important properties, including detail separability, detail transferability and detail idempotence.
Three new schemes are further designed for geometric surface detail processing applications, including geometric texture synthesis, geometry detail transfer, and 3D surface super-resolution.
- Score: 66.69000350849328
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With the rapid development of high-resolution 3D vision applications, the
traditional way of manipulating surface detail requires considerable memory and
computing time. To address these problems, we introduce an efficient surface
detail processing framework in 2D normal domain, which extracts new normal
feature representations as the carrier of micro geometry structures that are
illustrated both theoretically and empirically in this article. Compared with
the existing state of the arts, we verify and demonstrate that the proposed
normal-based representation has three important properties, including detail
separability, detail transferability and detail idempotence. Finally, three new
schemes are further designed for geometric surface detail processing
applications, including geometric texture synthesis, geometry detail transfer,
and 3D surface super-resolution. Theoretical analysis and experimental results
on the latest benchmark dataset verify the effectiveness and versatility of our
normal-based representation, which accepts 30 times of the input surface
vertices but at the same time only takes 6.5% memory cost and 14.0% running
time in comparison with existing competing algorithms.
Related papers
- 3D Hole Filling using Deep Learning Inpainting [0.0]
We propose a technique that incorporates neural network-based 2D inpainting to effectively reconstruct 3D surfaces.
Our customized neural networks were trained on a dataset containing over 1 million curvature images.
This strategy enables the system to learn and generalize patterns from input data, resulting in the development of precise and comprehensive three-dimensional surfaces.
arXiv Detail & Related papers (2024-07-25T09:36:37Z) - InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstruction [15.900375207144759]
3D surface reconstruction from multi-view images is essential for scene understanding and interaction.
Recent implicit surface representations, such as Neural Radiance Fields (NeRFs) and signed distance functions (SDFs) employ various geometric priors to resolve the lack of observed information.
We propose regularizing the geometric modeling by explicitly encouraging the mutual information among surface normals of highly correlated scene points.
arXiv Detail & Related papers (2024-07-17T15:46:25Z) - GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory.
Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images.
GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
arXiv Detail & Related papers (2024-06-21T17:49:31Z) - Flatten Anything: Unsupervised Neural Surface Parameterization [76.4422287292541]
We introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization.
Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information.
Our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies.
arXiv Detail & Related papers (2024-05-23T14:39:52Z) - Facial Geometric Detail Recovery via Implicit Representation [147.07961322377685]
We present a robust texture-guided geometric detail recovery approach using only a single in-the-wild facial image.
Our method combines high-quality texture completion with the powerful expressiveness of implicit surfaces.
Our method not only recovers accurate facial details but also decomposes normals, albedos, and shading parts in a self-supervised way.
arXiv Detail & Related papers (2022-03-18T01:42:59Z) - H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction [27.66008315400462]
Recent learning approaches that implicitly represent surface geometry have shown impressive results in the problem of multi-view 3D reconstruction.
We tackle these limitations for the specific problem of few-shot full 3D head reconstruction.
We learn a shape model of 3D heads from thousands of incomplete raw scans using implicit representations.
arXiv Detail & Related papers (2021-07-26T23:04:18Z) - ActivationNet: Representation learning to predict contact quality of
interacting 3-D surfaces in engineering designs [0.0]
In machine learning applications, 3-D surfaces are most suitably represented with point clouds or meshes.
This paper introduces a machine learning algorithm, ActivationNet, that can learn from point clouds or meshes of interacting 3-D surfaces and predict the quality of contact between these surfaces.
arXiv Detail & Related papers (2021-03-21T02:30:36Z) - Deep Active Surface Models [60.027353171412216]
Active Surface Models have a long history of being useful to model complex 3D surfaces but only Active Contours have been used in conjunction with deep networks.
We introduce layers that implement them that can be integrated seamlessly into Graph Convolutional Networks to enforce sophisticated smoothness priors.
arXiv Detail & Related papers (2020-11-17T18:48:28Z) - Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images [64.53227129573293]
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.
We design neural networks capable of generating high-quality parametric 3D surfaces which are consistent between views.
Our method is supervised and trained on a public dataset of shapes from common object categories.
arXiv Detail & Related papers (2020-08-18T06:33:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.