RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors

• URL: http://arxiv.org/abs/2503.10860v1
• Date: Thu, 13 Mar 2025 20:16:58 GMT
• Title: RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors
• Authors: Avinash Paliwal, Xilong Zhou, Wei Ye, Jinhui Xiong, Rakesh Ranjan, Nima Khademi Kalantari,
• Abstract summary: RI3D is a novel approach that harnesses the power of diffusion models to reconstruct high-quality novel views given a sparse set of input images.<n>Our key contribution is separating the view synthesis process into two tasks of reconstructing visible regions and hallucinating missing regions.<n>We produce results with detailed textures in both visible and missing regions that outperform state-of-the-art approaches on a diverse set of scenes.
• Score: 13.883695200241524
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose RI3D, a novel 3DGS-based approach that harnesses the power of diffusion models to reconstruct high-quality novel views given a sparse set of input images. Our key contribution is separating the view synthesis process into two tasks of reconstructing visible regions and hallucinating missing regions, and introducing two personalized diffusion models, each tailored to one of these tasks. Specifically, one model ('repair') takes a rendered image as input and predicts the corresponding high-quality image, which in turn is used as a pseudo ground truth image to constrain the optimization. The other model ('inpainting') primarily focuses on hallucinating details in unobserved areas. To integrate these models effectively, we introduce a two-stage optimization strategy: the first stage reconstructs visible areas using the repair model, and the second stage reconstructs missing regions with the inpainting model while ensuring coherence through further optimization. Moreover, we augment the optimization with a novel Gaussian initialization method that obtains per-image depth by combining 3D-consistent and smooth depth with highly detailed relative depth. We demonstrate that by separating the process into two tasks and addressing them with the repair and inpainting models, we produce results with detailed textures in both visible and missing regions that outperform state-of-the-art approaches on a diverse set of scenes with extremely sparse inputs.

Related papers

• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• CrossView-GS: Cross-view Gaussian Splatting For Large-scale Scene Reconstruction [5.528874948395173]
  3D Gaussian Splatting (3DGS) has emerged as a prominent method for scene representation and reconstruction.<n>We propose a novel cross-view Gaussian Splatting method for large-scale scene reconstruction, based on dual-branch fusion.<n>Our method achieves superior performance in novel view synthesis compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-03T08:24:59Z)
• LiftRefine: Progressively Refined View Synthesis from 3D Lifting with Volume-Triplane Representations [21.183524347952762]
  We propose a new view synthesis method via a 3D neural field from both single or few-view input images. Our reconstruction model first lifts one or more input images to the 3D space from a volume as the coarse-scale 3D representation. Our diffusion model then hallucinates missing details in the rendered images from tri-planes.
  arXiv  Detail & Related papers  (2024-12-19T02:23:55Z)
• GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction [79.42244344704154]
  GausSurf employs geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas of a scene.<n>Our method surpasses state-of-the-art methods in terms of reconstruction quality and computation time.
  arXiv  Detail & Related papers  (2024-11-29T03:54:54Z)
• DreamPolish: Domain Score Distillation With Progressive Geometry Generation [66.94803919328815]
  We introduce DreamPolish, a text-to-3D generation model that excels in producing refined geometry and high-quality textures. In the geometry construction phase, our approach leverages multiple neural representations to enhance the stability of the synthesis process. In the texture generation phase, we introduce a novel score distillation objective, namely domain score distillation (DSD), to guide neural representations toward such a domain.
  arXiv  Detail & Related papers  (2024-11-03T15:15:01Z)
• GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction [52.04103235260539]
  We present a diffusion model approach based on Gaussian Splatting representation for 3D object reconstruction from a single view. The model learns to generate 3D objects represented by sets of GS ellipsoids. The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views.
  arXiv  Detail & Related papers  (2024-07-05T03:43:08Z)
• InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior [36.23604779569843]
  3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points.
  arXiv  Detail & Related papers  (2024-04-17T17:59:53Z)
• NeuSD: Surface Completion with Multi-View Text-to-Image Diffusion [56.98287481620215]
  We present a novel method for 3D surface reconstruction from multiple images where only a part of the object of interest is captured. Our approach builds on two recent developments: surface reconstruction using neural radiance fields for the reconstruction of the visible parts of the surface, and guidance of pre-trained 2D diffusion models in the form of Score Distillation Sampling (SDS) to complete the shape in unobserved regions in a plausible manner.
  arXiv  Detail & Related papers  (2023-12-07T19:30:55Z)
• Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints [0.6749750044497732]
  We propose a two-stage training process, decouple view-dependent and view-independent colors, and leverage two novel consistency constraints to enhance detail reconstruction performance without requiring extra priors. Experiments on synthetic and real-world datasets show the capability of reducing the interference from prior estimation errors.
  arXiv  Detail & Related papers  (2023-09-18T13:05:23Z)
• Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis [16.14528024065244]
  "seesaw" problem: preserving reprojected contents and completing realistic out-of-view regions. We propose a single-image view synthesis framework for mitigating the seesaw problem while utilizing an efficient non-autoregressive model. Our loss function promotes synthesizing that explicit features improve the reprojected area of implicit features and implicit features improve the out-of-view area of explicit features.
  arXiv  Detail & Related papers  (2022-09-15T07:35:12Z)
• Differentiable Rendering with Perturbed Optimizers [85.66675707599782]
  Reasoning about 3D scenes from their 2D image projections is one of the core problems in computer vision. Our work highlights the link between some well-known differentiable formulations and randomly smoothed renderings. We apply our method to 3D scene reconstruction and demonstrate its advantages on the tasks of 6D pose estimation and 3D mesh reconstruction.
  arXiv  Detail & Related papers  (2021-10-18T08:56:23Z)
• Inverting Generative Adversarial Renderer for Face Reconstruction [58.45125455811038]
  In this work, we introduce a novel Generative Adversa Renderer (GAR) GAR learns to model the complicated real-world image, instead of relying on the graphics rules, it is capable of producing realistic images. Our method achieves state-of-the-art performances on multiple face reconstruction.
  arXiv  Detail & Related papers  (2021-05-06T04:16:06Z)

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.