VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors

Hugging Face Daily Papers Papers
3d-reconstruction gaussian-splatting video-diffusion generative-ai computer-vision sparse-input

Summary

VidSplat is a training-free generative reconstruction framework that uses video diffusion priors to recover complete 3D scenes from sparse inputs by synthesizing novel views.

Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are available. Although recent efforts alleviate this issue by enhancing multi-view consistency to produce plausible surfaces, they struggle to infer unseen, occluded, or weakly constrained regions beyond the input coverage. To address this limitation, we present VidSplat, a training-free generative reconstruction framework that leverages powerful video diffusion priors to iteratively synthesize novel views that compensate for missing input coverage, and thereby recover complete 3D scenes from sparse inputs. Specifically, we tackle two key challenges that enable the effective integration of generation and reconstruction. First, for 3D consistent generation, we elaborate a training-free, stage-wise denoising strategy that adaptively guides the denoising direction toward the underlying geometry using the rendered RGB and mask images. Second, to enhance the reconstruction, we develop an iterative mechanism that samples camera trajectories, explores unobserved regions, synthesizes novel views, and supplements training through confidence weighted refinement. VidSplat performs robustly to sparse input and even a single image. Extensive experiments on widely used benchmarks demonstrate our superior performance in sparse-view scene reconstruction.
Original Article
View Cached Full Text

Cached at: 05/13/26, 04:10 AM

Paper page - VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors

Source: https://huggingface.co/papers/2605.11424

Abstract

VidSplat is a training-free generative reconstruction framework that uses video diffusion priors to synthesize novel views and recover complete 3D scenes from sparse inputs through adaptive denoising and iterative refinement.

Gaussian Splattinghas achieved remarkable progress inmulti-view surface reconstruction, yet it exhibits notable degradation when only few views are available. Although recent efforts alleviate this issue by enhancing multi-view consistency to produce plausible surfaces, they struggle to infer unseen, occluded, or weakly constrained regions beyond the input coverage. To address this limitation, we present VidSplat, a training-free generative reconstruction framework that leverages powerfulvideo diffusion priorsto iteratively synthesize novel views that compensate for missing input coverage, and thereby recover complete 3D scenes from sparse inputs. Specifically, we tackle two key challenges that enable the effective integration of generation and reconstruction. First, for3D consistent generation, we elaborate a training-free, stage-wisedenoising strategythat adaptively guides the denoising direction toward the underlying geometry using the rendered RGB and mask images. Second, to enhance the reconstruction, we develop an iterative mechanism that samplescamera trajectories, explores unobserved regions, synthesizes novel views, and supplements training throughconfidence weighted refinement. VidSplat performs robustly to sparse input and even a single image. Extensive experiments on widely used benchmarks demonstrate our superior performance in sparse-view scene reconstruction.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.11424

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.11424 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.11424 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.11424 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Hugging Face Daily Papers

InfiniSplat presents a feed-forward single-image 3D Gaussian Splatting framework that uses geometry-guided sampling and query-conditioned implicit decoding to achieve surface-aligned Gaussian representation, improving large-baseline monocular view synthesis and generalizing from synthetic indoor training to open-world scenes.

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Hugging Face Daily Papers

GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.

FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation

Hugging Face Daily Papers

FLAT proposes a method to decode explicit triangle splats directly from video diffusion latents for geometrically accurate 3D scene generation. It introduces a ray-centered rotation parameterization and a product window function to improve gradient flow, achieving better geometric accuracy than prior feedforward methods while supporting real-time rendering.