3D Mesh Editing using Masked LRMs

• URL: http://arxiv.org/abs/2412.08641v1
• Date: Wed, 11 Dec 2024 18:59:17 GMT
• Title: 3D Mesh Editing using Masked LRMs
• Authors: Will Gao, Dilin Wang, Yuchen Fan, Aljaz Bozic, Tuur Stuyck, Zhengqin Li, Zhao Dong, Rakesh Ranjan, Nikolaos Sarafianos,
• Abstract summary: We present a novel approach to mesh shape editing, building on recent progress in 3D reconstruction from multi-view images. We formulate shape editing as a conditional reconstruction problem, where the model must reconstruct the input shape with the exception of a specified 3D region. We demonstrate that, in just a single forward pass, our method not only preserves the input geometry in the unmasked region through reconstruction capabilities on par with SoTA, but is also expressive enough to perform a variety of mesh edits from a single image guidance.
• Score: 26.34216998140891
• License:
• Abstract: We present a novel approach to mesh shape editing, building on recent progress in 3D reconstruction from multi-view images. We formulate shape editing as a conditional reconstruction problem, where the model must reconstruct the input shape with the exception of a specified 3D region, in which the geometry should be generated from the conditional signal. To this end, we train a conditional Large Reconstruction Model (LRM) for masked reconstruction, using multi-view consistent masks rendered from a randomly generated 3D occlusion, and using one clean viewpoint as the conditional signal. During inference, we manually define a 3D region to edit and provide an edited image from a canonical viewpoint to fill in that region. We demonstrate that, in just a single forward pass, our method not only preserves the input geometry in the unmasked region through reconstruction capabilities on par with SoTA, but is also expressive enough to perform a variety of mesh edits from a single image guidance that past works struggle with, while being 10x faster than the top-performing competing prior work.

Related papers

• FlexiDreamer: Single Image-to-3D Generation with FlexiCubes [20.871847154995688]
  FlexiDreamer is a novel framework that directly reconstructs high-quality meshes from multi-view generated images. Our approach can generate high-fidelity 3D meshes in the single image-to-3D downstream task with approximately 1 minute.
  arXiv  Detail & Related papers  (2024-04-01T08:20:18Z)
• Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement [78.48648360358193]
  We present a novel framework that generates textured surface meshes from images. Our approach begins by efficiently initializing the geometry and view-dependency appearance with a NeRF. We jointly refine the appearance with geometry and bake it into texture images for real-time rendering.
  arXiv  Detail & Related papers  (2023-03-03T17:14:44Z)
• Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion [115.82306502822412]
  StyleGAN has achieved great progress in 2D face reconstruction and semantic editing via image inversion and latent editing. A corresponding generic 3D GAN inversion framework is still missing, limiting the applications of 3D face reconstruction and semantic editing. We study the challenging problem of 3D GAN inversion where a latent code is predicted given a single face image to faithfully recover its 3D shapes and detailed textures.
  arXiv  Detail & Related papers  (2022-12-14T18:49:50Z)
• High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
  We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views. Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
  arXiv  Detail & Related papers  (2022-11-28T18:59:52Z)
• NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields [40.543998582101146]
  We introduce NeRFFaceEditing, which enables editing and decoupling geometry and appearance in neural radiance fields. Our method allows users to edit via semantic masks with decoupled control of geometry and appearance. Both qualitative and quantitative evaluations show the superior geometry and appearance control abilities of our method compared to existing and alternative solutions.
  arXiv  Detail & Related papers  (2022-11-15T08:11:39Z)
• Single-view 3D Mesh Reconstruction for Seen and Unseen Categories [69.29406107513621]
  Single-view 3D Mesh Reconstruction is a fundamental computer vision task that aims at recovering 3D shapes from single-view RGB images. This paper tackles Single-view 3D Mesh Reconstruction, to study the model generalization on unseen categories. We propose an end-to-end two-stage network, GenMesh, to break the category boundaries in reconstruction.
  arXiv  Detail & Related papers  (2022-08-04T14:13:35Z)
• 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)
• Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction [57.805334118057665]
  We propose REFINE, a postprocessing mesh refinement step that can be easily integrated into the pipeline of any black-box method in the literature. At test time, REFINE optimize a network per mesh instance, to encourage consistency between the mesh and the given object view.
  arXiv  Detail & Related papers  (2021-08-23T03:28:47Z)

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.