High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916619352014848 |
|---|---|
| author | Zhang, Xiang Zhang, Yang Mehl, Lukas Gross, Markus Schroers, Christopher |
| author_facet | Zhang, Xiang Zhang, Yang Mehl, Lukas Gross, Markus Schroers, Christopher |
| contents | Despite recent advances in Novel View Synthesis (NVS), generating high-fidelity views from single or sparse observations remains a significant challenge. Existing splatting-based approaches often produce distorted geometry due to splatting errors. While diffusion-based methods leverage rich 3D priors to achieve improved geometry, they often suffer from texture hallucination. In this paper, we introduce SplatDiff, a pixel-splatting-guided video diffusion model designed to synthesize high-fidelity novel views from a single image. Specifically, we propose an aligned synthesis strategy for precise control of target viewpoints and geometry-consistent view synthesis. To mitigate texture hallucination, we design a texture bridge module that enables high-fidelity texture generation through adaptive feature fusion. In this manner, SplatDiff leverages the strengths of splatting and diffusion to generate novel views with consistent geometry and high-fidelity details. Extensive experiments verify the state-of-the-art performance of SplatDiff in single-view NVS. Additionally, without extra training, SplatDiff shows remarkable zero-shot performance across diverse tasks, including sparse-view NVS and stereo video conversion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion Zhang, Xiang Zhang, Yang Mehl, Lukas Gross, Markus Schroers, Christopher Computer Vision and Pattern Recognition Despite recent advances in Novel View Synthesis (NVS), generating high-fidelity views from single or sparse observations remains a significant challenge. Existing splatting-based approaches often produce distorted geometry due to splatting errors. While diffusion-based methods leverage rich 3D priors to achieve improved geometry, they often suffer from texture hallucination. In this paper, we introduce SplatDiff, a pixel-splatting-guided video diffusion model designed to synthesize high-fidelity novel views from a single image. Specifically, we propose an aligned synthesis strategy for precise control of target viewpoints and geometry-consistent view synthesis. To mitigate texture hallucination, we design a texture bridge module that enables high-fidelity texture generation through adaptive feature fusion. In this manner, SplatDiff leverages the strengths of splatting and diffusion to generate novel views with consistent geometry and high-fidelity details. Extensive experiments verify the state-of-the-art performance of SplatDiff in single-view NVS. Additionally, without extra training, SplatDiff shows remarkable zero-shot performance across diverse tasks, including sparse-view NVS and stereo video conversion. |
| title | High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.12752 |