Neural Progressive Meshes

• URL: http://arxiv.org/abs/2308.05741v1
• Date: Thu, 10 Aug 2023 17:58:02 GMT
• Title: Neural Progressive Meshes
• Authors: Yun-Chun Chen, Vladimir G. Kim, Noam Aigerman, Alec Jacobson
• Abstract summary: We propose a method to transmit 3D meshes with a shared learned generative space. We learn this space using a subdivision-based encoder-decoder architecture trained in advance on a large collection of surfaces. We evaluate our method on a diverse set of complex 3D shapes and demonstrate that it outperforms baselines in terms of compression ratio and reconstruction quality.
• Score: 54.52990060976026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent proliferation of 3D content that can be consumed on hand-held devices necessitates efficient tools for transmitting large geometric data, e.g., 3D meshes, over the Internet. Detailed high-resolution assets can pose a challenge to storage as well as transmission bandwidth, and level-of-detail techniques are often used to transmit an asset using an appropriate bandwidth budget. It is especially desirable for these methods to transmit data progressively, improving the quality of the geometry with more data. Our key insight is that the geometric details of 3D meshes often exhibit similar local patterns even across different shapes, and thus can be effectively represented with a shared learned generative space. We learn this space using a subdivision-based encoder-decoder architecture trained in advance on a large collection of surfaces. We further observe that additional residual features can be transmitted progressively between intermediate levels of subdivision that enable the client to control the tradeoff between bandwidth cost and quality of reconstruction, providing a neural progressive mesh representation. We evaluate our method on a diverse set of complex 3D shapes and demonstrate that it outperforms baselines in terms of compression ratio and reconstruction quality.

Related papers

• DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow [44.72037991063735]
  DetailGen3D is a generative approach specifically designed to enhance generated 3D shapes. Our key insight is to model the coarse-to-fine transformation directly through data-dependent flows in latent space. We introduce a token matching strategy that ensures accurate spatial correspondence during refinement.
  arXiv  Detail & Related papers  (2024-11-25T17:08:17Z)
• An adversarial feature learning based semantic communication method for Human 3D Reconstruction [0.559239450391449]
  This paper introduces an Adversarial Feature Learning-based Semantic Communication method (AFLSC) for human body 3D reconstruction. We propose a multitask learning-based feature extraction method to capture the spatial layout, keypoints, posture, and depth information from 2D human images. We also design a semantic encoding technique based on adversarial feature learning to encode these feature information into semantic data.
  arXiv  Detail & Related papers  (2024-11-23T16:09:53Z)
• HIVE: HIerarchical Volume Encoding for Neural Implicit Surface Reconstruction [37.00102816748563]
  We introduce a volume encoding to explicitly encode the spatial information. High-resolution volumes capture the high-frequency geometry details. Low-resolution volumes enforce the spatial consistency to keep the shape smooth. This hierarchical volume encoding could be appended to any implicit surface reconstruction method as a plug-and-play module.
  arXiv  Detail & Related papers  (2024-08-03T06:34:20Z)
• GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image [94.56927147492738]
  We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes from single images. We show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. We propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions.
  arXiv  Detail & Related papers  (2024-03-18T17:50:41Z)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition [77.29516516532439]
  We design a frequency split network to generate 3D hand mesh using different frequency bands in a coarse-to-fine manner. To capture high-frequency personalized details, we transform the 3D mesh into the frequency domain, and propose a novel frequency decomposition loss. Our approach generates fine-grained details for high-fidelity 3D hand reconstruction.
  arXiv  Detail & Related papers  (2023-07-08T19:26:09Z)
• FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction [13.157400338544177]
  Recent works on 3D reconstruction from posed images have demonstrated that direct inference of scene-level 3D geometry is feasible using deep neural networks. We propose three effective solutions for improving the fidelity of inference-based 3D reconstructions. Our method, FineRecon, produces smooth and highly accurate reconstructions, showing significant improvements across multiple depth and 3D reconstruction metrics.
  arXiv  Detail & Related papers  (2023-04-04T02:50:29Z)
• Generating 3D structures from a 2D slice with GAN-based dimensionality expansion [0.0]
  Generative adversarial networks (GANs) can be trained to generate 3D image data, which is useful for design optimisation. We introduce a generative adversarial network architecture, SliceGAN, which is able to synthesise high fidelity 3D datasets using a single representative 2D image.
  arXiv  Detail & Related papers  (2021-02-10T18:46:17Z)
• Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation [79.78416804260668]
  We propose Spatial information guided Convolution (S-Conv), which allows efficient RGB feature and 3D spatial information integration. S-Conv is competent to infer the sampling offset of the convolution kernel guided by the 3D spatial information. We further embed S-Conv into a semantic segmentation network, called Spatial information Guided convolutional Network (SGNet)
  arXiv  Detail & Related papers  (2020-04-09T13:38:05Z)
• Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution [82.1739023587565]
  We propose a novel spectral-spatial residual network for hyperspectral image super-resolution (SSRNet) Our method can effectively explore spatial-spectral information by using 3D convolution instead of 2D convolution, which enables the network to better extract potential information. In each unit, we employ spatial and temporal separable 3D convolution to extract spatial and spectral information, which not only reduces unaffordable memory usage and high computational cost, but also makes the network easier to train.
  arXiv  Detail & Related papers  (2020-01-14T03:34:55Z)

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.