ReSplat: Learning Recurrent Gaussian Splats

• URL: http://arxiv.org/abs/2510.08575v1
• Date: Thu, 09 Oct 2025 17:59:59 GMT
• Title: ReSplat: Learning Recurrent Gaussian Splats
• Authors: Haofei Xu, Daniel Barath, Andreas Geiger, Marc Pollefeys,
• Abstract summary: ReSplat is a feed-forward recurrent Gaussian splatting model that iteratively refines 3D Gaussians without explicitly computing gradients.<n>We introduce a compact reconstruction model that operates in a $16 times$ subsampled space, producing $16 times$ fewer Gaussians than previous per-pixel Gaussian models.<n>Our method achieves state-of-the-art performance while significantly reducing the number of Gaussians and improving the rendering speed.
• Score: 98.14472247275512
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While feed-forward Gaussian splatting models provide computational efficiency and effectively handle sparse input settings, their performance is fundamentally limited by the reliance on a single forward pass during inference. We propose ReSplat, a feed-forward recurrent Gaussian splatting model that iteratively refines 3D Gaussians without explicitly computing gradients. Our key insight is that the Gaussian splatting rendering error serves as a rich feedback signal, guiding the recurrent network to learn effective Gaussian updates. This feedback signal naturally adapts to unseen data distributions at test time, enabling robust generalization. To initialize the recurrent process, we introduce a compact reconstruction model that operates in a $16 \times$ subsampled space, producing $16 \times$ fewer Gaussians than previous per-pixel Gaussian models. This substantially reduces computational overhead and allows for efficient Gaussian updates. Extensive experiments across varying of input views (2, 8, 16), resolutions ($256 \times 256$ to $540 \times 960$), and datasets (DL3DV and RealEstate10K) demonstrate that our method achieves state-of-the-art performance while significantly reducing the number of Gaussians and improving the rendering speed. Our project page is at https://haofeixu.github.io/resplat/.

Related papers

• iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion [62.09575122593993]
  iGaussian is a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion.<n> Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T&T+DB datasets demonstrate a significant performance improvement over previous methods.
  arXiv  Detail & Related papers  (2025-11-18T05:22:22Z)
• Second-order Optimization of Gaussian Splats with Importance Sampling [51.95046424364725]
  3D Gaussian Splatting (3DGS) is widely used for novel view rendering due to its high quality and fast inference time.<n>We propose a novel second-order optimization strategy based on Levenberg-Marquardt (LM) and Conjugate Gradient (CG)<n>Our method achieves a $3times$ speedup over standard LM and outperforms Adam by $6times$ when the Gaussian count is low.
  arXiv  Detail & Related papers  (2025-04-17T12:52:08Z)
• 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)
• Optimized Minimal 3D Gaussian Splatting [36.53860885419386]
  3D Gaussian Splatting (3DGS) has emerged as a powerful representation for real-time, high-performance rendering.<n> representing 3D scenes with numerous explicit Gaussian primitives imposes significant storage and memory overhead.<n>We propose a compact and precise attribute representation that efficiently captures both continuity and irregularity among primitives.
  arXiv  Detail & Related papers  (2025-03-21T07:41:45Z)
• MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks [10.860209186365344]
  3D Gaussian Splatting has demonstrated remarkable performance in novel view synthesis and real-time rendering.<n>However, the high memory consumption due to the use of millions of Gaussians limits its practicality.<n>We propose MaskGaussian, which models Gaussians as probabilistic entities rather than permanently removing them.
  arXiv  Detail & Related papers  (2024-12-29T17:12:16Z)
• 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)
• MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images [102.7646120414055]
  We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. On the large-scale RealEstate10K and ACID benchmarks, MVSplat achieves state-of-the-art performance with the fastest feed-forward inference speed (22fps)
  arXiv  Detail & Related papers  (2024-03-21T17:59:58Z)
• GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering [112.16239342037714]
  GES (Generalized Exponential Splatting) is a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks.
  arXiv  Detail & Related papers  (2024-02-15T17:32:50Z)
• SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering [24.91019554830571]
  We propose a method to allow precise and extremely fast mesh extraction from 3D Gaussian Splatting. It is however challenging to extract a mesh from the millions of tiny 3D gaussians as these gaussians tend to be unorganized after optimization.
  arXiv  Detail & Related papers  (2023-11-21T18:38:03Z)

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.