GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views

• URL: http://arxiv.org/abs/2602.22571v1
• Date: Thu, 26 Feb 2026 03:25:18 GMT
• Title: GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views
• Abstract summary: GIFSplat is a purely feed-forward iterative refinement framework for 3D Gaussian refineting from sparse unposed views.<n>It consistently outperforms state-of-the-art feed-forward baselines across DL3DV, RealEstate10K, and DTU.<n>It maintains second-scale inference time without requiring camera poses or any test-time gradient optimization.
• Score: 44.787835922271135
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feed-forward 3D reconstruction offers substantial runtime advantages over per-scene optimization, which remains slow at inference and often fragile under sparse views. However, existing feed-forward methods still have potential for further performance gains, especially for out-of-domain data, and struggle to retain second-level inference time once a generative prior is introduced. These limitations stem from the one-shot prediction paradigm in existing feed-forward pipeline: models are strictly bounded by capacity, lack inference-time refinement, and are ill-suited for continuously injecting generative priors. We introduce GIFSplat, a purely feed-forward iterative refinement framework for 3D Gaussian Splatting from sparse unposed views. A small number of forward-only residual updates progressively refine current 3D scene using rendering evidence, achieve favorable balance between efficiency and quality. Furthermore, we distill a frozen diffusion prior into Gaussian-level cues from enhanced novel renderings without gradient backpropagation or ever-increasing view-set expansion, thereby enabling per-scene adaptation with generative prior while preserving feed-forward efficiency. Across DL3DV, RealEstate10K, and DTU, GIFSplat consistently outperforms state-of-the-art feed-forward baselines, improving PSNR by up to +2.1 dB, and it maintains second-scale inference time without requiring camera poses or any test-time gradient optimization.

Related papers

• Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior [33.143169558717105]
  3D Gaussian Splatting (3DGS) achieves state-of-the-art rendering quality at real-time speeds but suffers from "model bloat"<n>This inefficiency stems from the standard "densify-then-prune" paradigm.<n>We present an efficient training framework that builds an intrinsically compact representation.
  arXiv  Detail & Related papers  (2026-08-23T10:21:30Z)
• EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams [108.45551580182384]
  EvTrajGS is an accurate and efficient 3D Gaussian Splatting framework for unposed event streams.<n>Our method enables reliable joint pose-scene optimization from coarse pose priors, eliminating the need for computationally expensive SLAM-style pipelines.
  arXiv  Detail & Related papers  (2026-08-09T09:00:30Z)
• From Uncertainty to Stability and Fidelity: Guiding Sparse-View 3D Gaussian Splatting with Fisher Information [55.09838774957981]
  3D Gaussian Splatting (3DGS) has emerged as a promising technique for novel view synthesis.<n>In sparse-view scenarios, 3DGS often prones to overfitting, resulting in noticeable artifacts and degraded rendering quality.<n>We propose a novel method for sparse-view 3DGS that incorporates Fisher Information to quantitatively guide the utilization of geometric priors and regularization.
  arXiv  Detail & Related papers  (2026-06-18T18:27:17Z)
• REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance [58.94345609736356]
  REFINE is a highly accelerated 3DGS pruning framework centered on a novel rendering-free primitive importance metric.<n>Experiments across multiple benchmark datasets demonstrate that REFINE maintains highly competitive rendering quality.
  arXiv  Detail & Related papers  (2026-06-08T06:16:38Z)
• ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting [65.02700555625749]
  ForeSplat is an optimization-aware training framework for feed-forward 3DGS models.<n>ForeSplat substantially reduces the capacity pressure on the feed-forward model.<n>It bridges the gap between amortized prediction and per-scene optimization.
  arXiv  Detail & Related papers  (2026-05-21T05:38:47Z)
• NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting [41.21645092733966]
  We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features.<n> Experiments show that our method enhances the accuracy of lifted semantics, providing an efficient and effective approach to robust 3D semantic Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-24T10:57:05Z)
• DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction [42.4365911571903]
  We propose DiffNR, a novel framework that enhances NR optimization with diffusion priors.<n>At its core is SliceFixer, a single-step diffusion model designed to correct artifacts in degraded slices.<n>In experiments, DiffNR improves PSNR by 3.99 dB on average, generalizes well across domains, and maintains efficient optimization.
  arXiv  Detail & Related papers  (2026-04-23T10:27:54Z)
• AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models [16.115612700186023]
  3D Gaussian Splatting (3DGS) is increasingly recognized as a powerful paradigm for real-time, high-fidelity 3D reconstruction.<n>Recently emerged feed-forward 3DGS models address these limitations by enabling fast reconstruction from a few input views after large-scale pretraining.<n>We introduce AdvSplat, the first systematic study of adversarial attacks on feed-forward 3DGS.
  arXiv  Detail & Related papers  (2026-03-24T19:48:23Z)
• EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images [39.67757218876105]
  EcoSplat is a feed-forward 3DGS framework that adaptively predicts the 3D representation for any given target primitive count at inference time.<n>We show that EcoSplat is robust and outperforms state-of-the-art methods under strict primitive-count constraints.
  arXiv  Detail & Related papers  (2025-12-21T11:12:48Z)
• RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS [79.15416002879239]
  3D Gaussian Splatting has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling.<n>Existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images.<n>We propose RobustSplat, a robust solution based on two critical designs.
  arXiv  Detail & Related papers  (2025-06-03T11:13:48Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesis [17.470869402542533]
  Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs.<n>We propose LL-Gaussian, a novel framework for 3D reconstruction and enhancement from low-light sRGB images.<n>Compared to state-of-the-art NeRF-based methods, LL-Gaussian achieves up to 2,000 times faster inference and reduces training time to just 2%.
  arXiv  Detail & Related papers  (2025-04-14T15:39:31Z)
• FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction [50.534213038479926]
  FreeSplat++ is an alternative approach to large-scale indoor whole-scene reconstruction.<n>Our method with depth-regularized per-scene fine-tuning demonstrates substantial improvements in reconstruction accuracy and a notable reduction in training time.
  arXiv  Detail & Related papers  (2025-03-29T06:22:08Z)
• How to Use Diffusion Priors under Sparse Views? [29.738350228085928]
  Inline Prior Guided Score Matching is proposed to provide visual supervision over sparse views in 3D reconstruction.<n>We show that our method achieves state-of-the-art reconstruction quality.
  arXiv  Detail & Related papers  (2024-12-03T07:31:54Z)
• ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions [91.55655961014027]
  3D semantic occupancy and flow prediction are fundamental to understanding scene scene.<n>This paper proposes a vision-based framework with three targeted improvements.<n>Our purely convolutional architecture establishes new SOTA performance on multiple benchmarks for both semantic occupancy and joint semantic-flow prediction.
  arXiv  Detail & Related papers  (2024-11-12T11:32:56Z)
• Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting [60.393072253444934]
  We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks. We identify a divergence between the diffusion priors and the training procedures of diffusion models that substantially impairs the quality of 3D generation.
  arXiv  Detail & Related papers  (2023-12-08T03:55:34Z)
• Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation [29.430404703883084]
  We present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. The proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model.
  arXiv  Detail & Related papers  (2022-03-15T07:30:27Z)

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.