Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction

• URL: http://arxiv.org/abs/2604.04874v1
• Date: Mon, 06 Apr 2026 17:24:18 GMT
• Title: Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
• Abstract summary: Free-Range Gaussians is a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images.<n>Our generative formulation of reconstruction allows the model to be supervised with non-grid-aligned 3D data.
• Score: 72.85652875805387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Free-Range Gaussians, a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images. This is done through flow matching over Gaussian parameters. Our generative formulation of reconstruction allows the model to be supervised with non-grid-aligned 3D data, and enables it to synthesize plausible content in unobserved regions. Thus, it improves on prior methods that produce highly redundant grid-aligned Gaussians, and suffer from holes or blurry conditional means in unobserved regions. To handle the number of Gaussians needed for high-quality results, we introduce a hierarchical patching scheme to group spatially related Gaussians into joint transformer tokens, halving the sequence length while preserving structure. We further propose a timestep-weighted rendering loss during training, and photometric gradient guidance and classifier-free guidance at inference to improve fidelity. Experiments on Objaverse and Google Scanned Objects show consistent improvements over pixel and voxel-aligned methods while using significantly fewer Gaussians, with large gains when input views leave parts of the object unobserved.

Related papers

• AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors [23.943522711585597]
  We propose AnchorSplat, a novel feed-forward 3DGS framework for scene-level reconstruction.<n> anchor-aligned Gaussian representation guided by 3D geometric priors.<n>Design substantially reduces the number of required Gaussians.
  arXiv  Detail & Related papers  (2026-04-08T13:04:54Z)
• GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidance [60.86483080195698]
  3D Gaussian Splatting has demonstrated superior performance in rendering efficiency and quality.<n>Existing methods have explored predicting point maps as geometric references for inferring Gaussian primitives.<n>We introduce GaussianGrow, a novel approach that generates 3D Gaussians by learning to grow them from easily accessible 3D point clouds.
  arXiv  Detail & Related papers  (2026-04-07T11:23:23Z)
• F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting [28.800888081472422]
  We present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting.<n>Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget.<n>Experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods.
  arXiv  Detail & Related papers  (2026-03-22T16:03:56Z)
• ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes [81.48624894781257]
  3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required.<n>Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency.<n>We propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality.
  arXiv  Detail & Related papers  (2025-03-21T18:55:14Z)
• GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance [43.97159590077809]
  We present GaussianPainter, the first method to paint a point cloud into 3D Gaussians given a reference image.<n>Our method addresses the non-uniqueness problem inherent in the large parameter space of 3D Gaussian splatting.
  arXiv  Detail & Related papers  (2024-12-23T16:45:37Z)
• PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views [116.10577967146762]
  PixelGaussian is an efficient framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Our method achieves state-of-the-art performance with good generalization to various numbers of views.
  arXiv  Detail & Related papers  (2024-10-24T17:59:58Z)
• Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting [33.01987451251659]
  3D Gaussian Splatting (3DGS) has emerged as a promising technique capable of real-time rendering with high-quality 3D reconstruction.<n>Despite its potential, 3DGS encounters challenges such as needle-like artifacts, suboptimal geometries, and inaccurate normals.<n>We introduce the effective rank as a regularization, which constrains the structure of the Gaussians.
  arXiv  Detail & Related papers  (2024-06-17T15:51:59Z)
• Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes [50.92217884840301]
  Gaussian Opacity Fields (GOF) is a novel approach for efficient, high-quality, and adaptive surface reconstruction in scenes. GOF is derived from ray-tracing-based volume rendering of 3D Gaussians. GOF surpasses existing 3DGS-based methods in surface reconstruction and novel view synthesis.
  arXiv  Detail & Related papers  (2024-04-16T17:57:19Z)
• Mesh-based Gaussian Splatting for Real-time Large-scale Deformation [58.18290393082119]
  It is challenging for users to directly deform or manipulate implicit representations with large deformations in the real-time fashion. We develop a novel GS-based method that enables interactive deformation. Our approach achieves high-quality reconstruction and effective deformation, while maintaining the promising rendering results at a high frame rate.
  arXiv  Detail & Related papers  (2024-02-07T12:36:54Z)

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.