MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

• URL: http://arxiv.org/abs/2503.08664v1
• Date: Tue, 11 Mar 2025 17:50:59 GMT
• Title: MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
• Authors: Yuhan Wang, Fangzhou Hong, Shuai Yang, Liming Jiang, Wayne Wu, Chen Change Loy,
• Abstract summary: We introduce a solution called mesh attention to enable training at 1024x1024 resolution.<n>This approach significantly reduces the complexity of multiview attention while maintaining cross-view consistency.<n>Building on this foundation, we devise a mesh attention block and combine it with keypoint conditioning to create our human-specific multiview diffusion model, MEAT.
• Score: 83.56588173102594
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multiview diffusion models have shown considerable success in image-to-3D generation for general objects. However, when applied to human data, existing methods have yet to deliver promising results, largely due to the challenges of scaling multiview attention to higher resolutions. In this paper, we explore human multiview diffusion models at the megapixel level and introduce a solution called mesh attention to enable training at 1024x1024 resolution. Using a clothed human mesh as a central coarse geometric representation, the proposed mesh attention leverages rasterization and projection to establish direct cross-view coordinate correspondences. This approach significantly reduces the complexity of multiview attention while maintaining cross-view consistency. Building on this foundation, we devise a mesh attention block and combine it with keypoint conditioning to create our human-specific multiview diffusion model, MEAT. In addition, we present valuable insights into applying multiview human motion videos for diffusion training, addressing the longstanding issue of data scarcity. Extensive experiments show that MEAT effectively generates dense, consistent multiview human images at the megapixel level, outperforming existing multiview diffusion methods.

Related papers

• Pixel-Aligned Multi-View Generation with Depth Guided Decoder [86.1813201212539]
  We propose a novel method for pixel-level image-to-multi-view generation. Unlike prior work, we incorporate attention layers across multi-view images in the VAE decoder of a latent video diffusion model. Our model enables better pixel alignment across multi-view images.
  arXiv  Detail & Related papers  (2024-08-26T04:56:41Z)
• Vivid-ZOO: Multi-View Video Generation with Diffusion Model [76.96449336578286]
  New challenges lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. We propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text.
  arXiv  Detail & Related papers  (2024-06-12T21:44:04Z)
• Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention [87.02613021058484]
  We introduce Era3D, a novel multiview diffusion method that generates high-resolution multiview images from a single-view image.<n>Era3D generates high-quality multiview images with up to a 512*512 resolution while reducing complexity by 12x times.
  arXiv  Detail & Related papers  (2024-05-19T17:13:16Z)
• Multi-view Aggregation Network for Dichotomous Image Segmentation [76.75904424539543]
  Dichotomous Image (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. Existing methods rely on tedious multiple encoder-decoder streams and stages to gradually complete the global localization and local refinement. Inspired by it, we model DIS as a multi-view object perception problem and provide a parsimonious multi-view aggregation network (MVANet) Experiments on the popular DIS-5K dataset show that our MVANet significantly outperforms state-of-the-art methods in both accuracy and speed.
  arXiv  Detail & Related papers  (2024-04-11T03:00:00Z)
• EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion [60.30030562932703]
  EpiDiff is a localized interactive multiview diffusion model. It generates 16 multiview images in just 12 seconds. It surpasses previous methods in quality evaluation metrics.
  arXiv  Detail & Related papers  (2023-12-11T05:20:52Z)

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.