VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909035159093248 |
|---|---|
| author | Tang, Jimin Zhang, Wenyuan Zhou, Junsheng Huang, Zian Shi, Kanle Xu, Shenkun Liu, Yu-Shen Han, Zhizhong |
| author_facet | Tang, Jimin Zhang, Wenyuan Zhou, Junsheng Huang, Zian Shi, Kanle Xu, Shenkun Liu, Yu-Shen Han, Zhizhong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11424 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors Tang, Jimin Zhang, Wenyuan Zhou, Junsheng Huang, Zian Shi, Kanle Xu, Shenkun Liu, Yu-Shen Han, Zhizhong Computer Vision and Pattern Recognition 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. |
| title | VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.11424 |