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

• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images [45.051325655043634]
  We introduce a novel multi-task learning (MTL) network that simultaneously estimates depth and surface normals from 360deg images. Experimental results demonstrate that our MTL architecture significantly outperforms state-of-the-art methods in both depth and surface normal estimation. Our model's effectiveness and generalizability, particularly in handling intricate surface textures, establish it as a new benchmark in 360deg image geometric estimation.
  arXiv  Detail & Related papers  (2024-11-04T02:20:22Z)
• GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction [71.08607897266045]
  3D Gaussian Splatting (3DGS) has shown promising performance in novel view synthesis. We make the first attempt to tackle the challenging task of large-scale scene surface reconstruction. We propose GigaGS, the first work for high-quality surface reconstruction for large-scale scenes using 3DGS.
  arXiv  Detail & Related papers  (2024-09-10T17:51:39Z)
• Spurfies: Sparse Surface Reconstruction using Local Geometry Priors [8.260048622127913]
  We introduce Spurfies, a novel method for sparse-view surface reconstruction. It disentangles appearance and geometry information to utilize local geometry priors trained on synthetic data. We validate our method on the DTU dataset and demonstrate that it outperforms previous state of the art by 35% in surface quality.
  arXiv  Detail & Related papers  (2024-08-29T14:02:47Z)
• 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)
• 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.