Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors

• URL: http://arxiv.org/abs/2411.15966v1
• Date: Sun, 24 Nov 2024 19:34:58 GMT
• Title: Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
• Authors: Soumava Paul, Prakhar Kaushik, Alan Yuille,
• Abstract summary: We introduce a generative approach for pose-free reconstruction of $360circ$ scenes from a limited number of uncalibrated 2D images. We propose an instruction-following RGBD diffusion model designed to inpaint missing details and remove artifacts in novel view renders and depth maps of a 3D scene.
• Score: 5.407319151576265
• License:
• Abstract: In this work, we introduce a generative approach for pose-free reconstruction of $360^{\circ}$ scenes from a limited number of uncalibrated 2D images. Pose-free scene reconstruction from incomplete, unposed observations is usually regularized with depth estimation or 3D foundational priors. While recent advances have enabled sparse-view reconstruction of unbounded scenes with known camera poses using diffusion priors, these methods rely on explicit camera embeddings for extrapolating unobserved regions. This reliance limits their application in pose-free settings, where view-specific data is only implicitly available. To address this, we propose an instruction-following RGBD diffusion model designed to inpaint missing details and remove artifacts in novel view renders and depth maps of a 3D scene. We also propose a novel confidence measure for Gaussian representations to allow for better detection of these artifacts. By progressively integrating these novel views in a Gaussian-SLAM-inspired process, we achieve a multi-view-consistent Gaussian representation. Evaluations on the MipNeRF360 dataset demonstrate that our method surpasses existing pose-free techniques and performs competitively with state-of-the-art posed reconstruction methods in complex $360^{\circ}$ scenes.

Related papers

• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• SCube: Instant Large-Scale Scene Reconstruction using VoxSplats [55.383993296042526]
  We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry, appearance, and semantics) from a sparse set of posed images. Our method encodes reconstructed scenes using a novel representation VoxSplat, which is a set of 3D Gaussians supported on a high-resolution sparse-voxel scaffold.
  arXiv  Detail & Related papers  (2024-10-26T00:52:46Z)
• LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors [34.91966359570867]
  sparse-view reconstruction is inherently ill-posed and under-constrained. We introduce LM-Gaussian, a method capable of generating high-quality reconstructions from a limited number of images. Our approach significantly reduces the data acquisition requirements compared to previous 3DGS methods.
  arXiv  Detail & Related papers  (2024-09-05T12:09:02Z)
• Sp2360: Sparse-view 360 Scene Reconstruction using Cascaded 2D Diffusion Priors [51.36238367193988]
  We tackle sparse-view reconstruction of a 360 3D scene using priors from latent diffusion models (LDM) We present SparseSplat360, a method that employs a cascade of in-painting and artifact removal models to fill in missing details and clean novel views. Our method generates entire 360 scenes from as few as 9 input views, with a high degree of foreground and background detail.
  arXiv  Detail & Related papers  (2024-05-26T11:01:39Z)
• GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views [9.175560202201819]
  3D Gaussian Splatting (3DGS) has emerged as an efficient approach for accurately representing scenes. We propose a novel approach for bridging the gap between the noisy 3DGS representation and the smooth 3D mesh representation. We render stereo-aligned pairs of images corresponding to the original training poses, feed the pairs into a stereo model to get a depth profile, and finally fuse all of the profiles together to get a single mesh.
  arXiv  Detail & Related papers  (2024-04-02T10:13:18Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• Enhancement of Novel View Synthesis Using Omnidirectional Image Completion [61.78187618370681]
  We present a method for synthesizing novel views from a single 360-degree RGB-D image based on the neural radiance field (NeRF) Experiments demonstrated that the proposed method can synthesize plausible novel views while preserving the features of the scene for both artificial and real-world data.
  arXiv  Detail & Related papers  (2022-03-18T13:49:25Z)
• ERF: Explicit Radiance Field Reconstruction From Scratch [12.254150867994163]
  We propose a novel explicit dense 3D reconstruction approach that processes a set of images of a scene with sensor poses and calibrations and estimates a photo-real digital model. One of the key innovations is that the underlying volumetric representation is completely explicit. We show that our method is general and practical. It does not require a highly controlled lab setup for capturing, but allows for reconstructing scenes with a vast variety of objects.
  arXiv  Detail & Related papers  (2022-02-28T19:37:12Z)
• Learning to Recover 3D Scene Shape from a Single Image [98.20106822614392]
  We propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image. We then use 3D point cloud encoders to predict the missing depth shift and focal length that allow us to recover a realistic 3D scene shape.
  arXiv  Detail & Related papers  (2020-12-17T02:35:13Z)

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.