Generalizable Sparse-View 3D Reconstruction from Unconstrained Images

• URL: http://arxiv.org/abs/2604.28193v1
• Date: Thu, 30 Apr 2026 17:59:55 GMT
• Title: Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
• Abstract summary: GenWildSplat is a feed-forward framework for sparse-view outdoor reconstruction.<n>It predicts depth, camera parameters, and 3D Gaussians in a canonical space.<n>It generalizes across diverse illumination and occlusion patterns.
• Score: 34.49488901858801
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on scene-specific optimization using appearance embeddings or dynamic masks, which requires extensive per-scene training and fails under sparse views. Moreover, evaluations on limited scenes raise questions about generalization. We present GenWildSplat, a feed-forward framework for sparse-view outdoor reconstruction that requires no per-scene optimization. Given unposed internet images, GenWildSplat predicts depth, camera parameters, and 3D Gaussians in a canonical space using learned geometric priors. An appearance adapter modulates appearance for target lighting conditions, while semantic segmentation handles transient objects. Through curriculum learning on synthetic and real data, GenWildSplat generalizes across diverse illumination and occlusion patterns. Evaluations on PhotoTourism and MegaScenes benchmark demonstrate state-of-the-art feed-forward rendering quality, achieving real-time inference without test-time optimization

Related papers

• Wild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection [30.884035795245946]
  We present Wild3R, a feed-forward approach for unconstrained sparse photo collections.<n>Our model learns appearance consistency across viewpoints conditioned on reference views, while removing transient content.
  arXiv  Detail & Related papers  (2026-06-10T10:23:06Z)
• WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images [8.46439977025813]
  WildSplatter is a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions.<n>We jointly learn 3D Gaussians and appearance embeddings conditioned on input images.<n>Our method reconstructs 3D Gaussians from sparse input views in under one second, while also enabling appearance control under diverse lighting conditions.
  arXiv  Detail & Related papers  (2026-04-23T00:58:43Z)
• R3GW: Relightable 3D Gaussians for Outdoor Scenes in the Wild [23.68389428693905]
  3D Gaussian Splatting (3DGS) has established itself as a leading technique for 3D reconstruction and novel view synthesis of static scenes.<n>We present R3GW, a novel method that learns a relightable 3DGS representation of an outdoor scene captured in the wild.
  arXiv  Detail & Related papers  (2026-03-03T09:40:16Z)
• OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View [74.58230239274123]
  We propose OGGSplat, an open Gaussian growing method that expands the field-of-view in generalizable 3D reconstruction.<n>Our key insight is that the semantic attributes of open Gaussians provide strong priors for image extrapolation.<n> OGGSplat also demonstrates promising semantic-aware scene reconstruction capabilities when provided with two view images captured directly from a smartphone camera.
  arXiv  Detail & Related papers  (2025-06-05T16:17:18Z)
• AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views [68.94737256959661]
  AnySplat is a feed forward network for novel view synthesis from uncalibrated image collections.<n>A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance.<n>In extensive zero shot evaluations, AnySplat matches the quality of pose aware baselines in both sparse and dense view scenarios.
  arXiv  Detail & Related papers  (2025-05-29T17:49:56Z)
• SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative Priors [22.561786156613525]
  We propose SparseGS-W, a novel framework to Synthesizing novel views of large-scale scenes from unconstrained in-the-wild images.<n>We leverage geometric priors and constrained diffusion priors to compensate for the lack of multi-view information from extremely sparse input.<n>SparseGS-W achieves state-of-the-art performance not only in full-reference metrics, but also in commonly used non-reference metrics such as FID, ClipIQA, and MUSIQ.
  arXiv  Detail & Related papers  (2025-03-25T08:40:40Z)
• Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors [8.440211083233528]
  We introduce a generative approach for pose-free (without camera parameters) reconstruction of 360 scenes from a sparse set of 2D images.<n>We propose an image-to-image generative model designed to inpaint missing details and remove artifacts in novel view renders and depth maps of a 3D scene.
  arXiv  Detail & Related papers  (2024-11-24T19:34:58Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)
• MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering [91.76893697171117]
  We propose a method for efficient and high-quality geometry recovery and novel view synthesis given very sparse or even a single view of the human. Our key idea is to meta-learn the radiance field weights solely from potentially sparse multi-view videos. We collect a new dataset, WildDynaCap, which contains subjects captured in, both, a dense camera dome and in-the-wild sparse camera rigs.
  arXiv  Detail & Related papers  (2024-03-27T17:59:54Z)
• VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction [59.40711222096875]
  We present VastGaussian, the first method for high-quality reconstruction and real-time rendering on large scenes based on 3D Gaussian Splatting. Our approach outperforms existing NeRF-based methods and achieves state-of-the-art results on multiple large scene datasets.
  arXiv  Detail & Related papers  (2024-02-27T11:40:50Z)
• 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)

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.