T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image

• URL: http://arxiv.org/abs/2403.13663v1
• Date: Wed, 20 Mar 2024 15:14:22 GMT
• Title: T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image
• Authors: Shijie Zhang, Boyan Jiang, Keke He, Junwei Zhu, Ying Tai, Chengjie Wang, Yinda Zhang, Yanwei Fu,
• Abstract summary: We propose a novel Transformer-boosted architecture, named T-Pixel2Mesh, inspired by the coarse-to-fine approach of P2M. Specifically, we use a global Transformer to control the holistic shape and a local Transformer to refine the local geometry details. Our experiments on ShapeNet demonstrate state-of-the-art performance, while results on real-world data show the generalization capability.
• Score: 84.08705684778666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pixel2Mesh (P2M) is a classical approach for reconstructing 3D shapes from a single color image through coarse-to-fine mesh deformation. Although P2M is capable of generating plausible global shapes, its Graph Convolution Network (GCN) often produces overly smooth results, causing the loss of fine-grained geometry details. Moreover, P2M generates non-credible features for occluded regions and struggles with the domain gap from synthetic data to real-world images, which is a common challenge for single-view 3D reconstruction methods. To address these challenges, we propose a novel Transformer-boosted architecture, named T-Pixel2Mesh, inspired by the coarse-to-fine approach of P2M. Specifically, we use a global Transformer to control the holistic shape and a local Transformer to progressively refine the local geometry details with graph-based point upsampling. To enhance real-world reconstruction, we present the simple yet effective Linear Scale Search (LSS), which serves as prompt tuning during the input preprocessing. Our experiments on ShapeNet demonstrate state-of-the-art performance, while results on real-world data show the generalization capability.

Related papers

• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• Double-Shot 3D Shape Measurement with a Dual-Branch Network [14.749887303860717]
  We propose a dual-branch Convolutional Neural Network (CNN)-Transformer network (PDCNet) to process different structured light (SL) modalities. Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images. We show that our method can reduce fringe order ambiguity while producing high-accuracy results on a self-made dataset.
  arXiv  Detail & Related papers  (2024-07-19T10:49:26Z)
• 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)
• 3Deformer: A Common Framework for Image-Guided Mesh Deformation [27.732389685912214]
  Given a source 3D mesh with semantic materials, and a user-specified semantic image, 3Deformer can accurately edit the source mesh. Our 3Deformer is able to produce impressive results and reaches the state-of-the-art level.
  arXiv  Detail & Related papers  (2023-07-19T10:44:44Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape [77.95154911528365]
  3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. Previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry. This paper proposes a complete solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person.
  arXiv  Detail & Related papers  (2022-04-09T03:46:18Z)
• D$^2$IM-Net: Learning Detail Disentangled Implicit Fields from Single Images [6.121310352120004]
  We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image. Our key idea is to train the network to learn a detail disentangled reconstruction consisting of two functions.
  arXiv  Detail & Related papers  (2020-12-11T21:42:52Z)
• Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction [97.3274868990133]
  Geo-PIFu is a method to recover a 3D mesh from a monocular color image of a clothed person. We show that, by both encoding query points and constraining global shape using latent voxel features, the reconstruction we obtain for clothed human meshes exhibits less shape distortion and improved surface details compared to competing methods.
  arXiv  Detail & Related papers  (2020-06-15T01:11:48Z)

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.