Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.27422 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909003631558656 |
|---|---|
| author | Park, Wongi James, Jordan A. Nam, Myeongseok Lee, Minjae Lee, Soomok Lee, Sang-Hyun Beksi, William J. |
| author_facet | Park, Wongi James, Jordan A. Nam, Myeongseok Lee, Minjae Lee, Soomok Lee, Sang-Hyun Beksi, William J. |
| contents | We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without transient elements or leverage unconstrained dense image collections to enhance 3D representation in real-world scenarios, our method not only effectively tackles sparse unconstrained image collections, but also shows high-quality 3D rendering results. To do this, we introduce reference-guided view refinement with a diffusion model using a transient mask and a reference image to enhance the 3D representation and mitigate artifacts in rendered views. Furthermore, we address sparse regions in the Gaussian field via pseudo-view generation along with a sparsity-aware Gaussian replication strategy to amplify Gaussians in the sparse regions. Extensive experiments on publicly available datasets demonstrate that our methodology consistently outperforms existing methods (e.g., PSNR - 17.2%, SSIM - 10.8%, LPIPS - 4.0%) and provides high-fidelity 3D rendering results. This advancement paves the way for realizing unconstrained real-world scenarios without labor-intensive data acquisition. Our project page is available at $\href{https://robotic-vision-lab.github.io/SaveWildGS/}{here}$ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27422 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sparse-View 3D Gaussian Splatting in the Wild Park, Wongi James, Jordan A. Nam, Myeongseok Lee, Minjae Lee, Soomok Lee, Sang-Hyun Beksi, William J. Computer Vision and Pattern Recognition We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without transient elements or leverage unconstrained dense image collections to enhance 3D representation in real-world scenarios, our method not only effectively tackles sparse unconstrained image collections, but also shows high-quality 3D rendering results. To do this, we introduce reference-guided view refinement with a diffusion model using a transient mask and a reference image to enhance the 3D representation and mitigate artifacts in rendered views. Furthermore, we address sparse regions in the Gaussian field via pseudo-view generation along with a sparsity-aware Gaussian replication strategy to amplify Gaussians in the sparse regions. Extensive experiments on publicly available datasets demonstrate that our methodology consistently outperforms existing methods (e.g., PSNR - 17.2%, SSIM - 10.8%, LPIPS - 4.0%) and provides high-fidelity 3D rendering results. This advancement paves the way for realizing unconstrained real-world scenarios without labor-intensive data acquisition. Our project page is available at $\href{https://robotic-vision-lab.github.io/SaveWildGS/}{here}$ |
| title | Sparse-View 3D Gaussian Splatting in the Wild |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.27422 |