MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing

• URL: http://arxiv.org/abs/2408.08000v2
• Date: Sun, 3 Nov 2024 02:01:56 GMT
• Title: MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
• Authors: Chenjie Cao, Chaohui Yu, Fan Wang, Xiangyang Xue, Yanwei Fu,
• Abstract summary: Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. We propose MVInpainter, re-formulating the 3D editing as a multi-view 2D inpainting task. MVInpainter partially inpaints multi-view images with the reference guidance rather than intractably generating an entirely novel view from scratch.
• Score: 90.30646271720919
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. However, these works mainly focus on confined categories or synthetic 3D assets, which are discouraged from generalizing to challenging in-the-wild scenes and fail to be employed with 2D synthesis directly. Moreover, these methods heavily depended on camera poses, limiting their real-world applications. To overcome these issues, we propose MVInpainter, re-formulating the 3D editing as a multi-view 2D inpainting task. Specifically, MVInpainter partially inpaints multi-view images with the reference guidance rather than intractably generating an entirely novel view from scratch, which largely simplifies the difficulty of in-the-wild NVS and leverages unmasked clues instead of explicit pose conditions. To ensure cross-view consistency, MVInpainter is enhanced by video priors from motion components and appearance guidance from concatenated reference key&value attention. Furthermore, MVInpainter incorporates slot attention to aggregate high-level optical flow features from unmasked regions to control the camera movement with pose-free training and inference. Sufficient scene-level experiments on both object-centric and forward-facing datasets verify the effectiveness of MVInpainter, including diverse tasks, such as multi-view object removal, synthesis, insertion, and replacement. The project page is https://ewrfcas.github.io/MVInpainter/.

Related papers

• MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D [63.9188712646076]
  Texturing is a 3D asset production, which enhances the visual appeal and visual appeal. Despite recent advancements, methods often yield subpar results, primarily due to local discontinuities. We propose a novel framework called MVPaint, which can generate high-resolution, seamless multiview consistency.
  arXiv  Detail & Related papers  (2024-11-04T17:59:39Z)
• Shape of Motion: 4D Reconstruction from a Single Video [51.04575075620677]
  We introduce a method capable of reconstructing generic dynamic scenes, featuring explicit, full-sequence-long 3D motion. We exploit the low-dimensional structure of 3D motion by representing scene motion with a compact set of SE3 motion bases. Our method achieves state-of-the-art performance for both long-range 3D/2D motion estimation and novel view synthesis on dynamic scenes.
  arXiv  Detail & Related papers  (2024-07-18T17:59:08Z)
• NeRFiller: Completing Scenes via Generative 3D Inpainting [113.18181179986172]
  We propose NeRFiller, an approach that completes missing portions of a 3D capture via generative 3D inpainting. In contrast to related works, we focus on completing scenes rather than deleting foreground objects.
  arXiv  Detail & Related papers  (2023-12-07T18:59:41Z)
• OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields [53.32527220134249]
  The emergence of Neural Radiance Fields (NeRF) for novel view synthesis has increased interest in 3D scene editing. Current methods face challenges such as time-consuming object labeling, limited capability to remove specific targets, and compromised rendering quality after removal. This paper proposes a novel object-removing pipeline, named OR-NeRF, that can remove objects from 3D scenes with user-given points or text prompts on a single view.
  arXiv  Detail & Related papers  (2023-05-17T18:18:05Z)
• Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting [10.087325516269265]
  We present an automatic system that removes clutter from 3D scenes and inpaints with coherent geometry and texture. We group noisy fine-grained labels, leverage virtual rendering, and impose an instance-level area-sensitive loss. Experiments on ScanNet and Matterport dataset show that our method outperforms baselines for clutter segmentation and 3D inpainting.
  arXiv  Detail & Related papers  (2023-04-07T17:57:20Z)
• Decoupling Dynamic Monocular Videos for Dynamic View Synthesis [50.93409250217699]
  We tackle the challenge of dynamic view synthesis from dynamic monocular videos in an unsupervised fashion. Specifically, we decouple the motion of the dynamic objects into object motion and camera motion, respectively regularized by proposed unsupervised surface consistency and patch-based multi-view constraints.
  arXiv  Detail & Related papers  (2023-04-04T11:25:44Z)
• SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields [26.296017756560467]
  In 3D, solutions must be consistent across multiple views and geometrically valid. We propose a novel 3D inpainting method that addresses these challenges. We first demonstrate the superiority of our approach on multiview segmentation, comparing to NeRFbased methods and 2D segmentation approaches.
  arXiv  Detail & Related papers  (2022-11-22T13:14:50Z)

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.