Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914251498586112 |
|---|---|
| author | Tsalakopoulos, Anastasios Kanlis, Angelos Chatzis, Evangelos Karakottas, Antonis Zarpalas, Dimitrios |
| author_facet | Tsalakopoulos, Anastasios Kanlis, Angelos Chatzis, Evangelos Karakottas, Antonis Zarpalas, Dimitrios |
| contents | We introduce Geo-NVS-w, a geometry-aware framework for high-fidelity novel view synthesis from unstructured, in-the-wild image collections. While existing in-the-wild methods already excel at novel view synthesis, they often lack geometric grounding on complex surfaces, sometimes producing results that contain inconsistencies. Geo-NVS-w addresses this limitation by leveraging an underlying geometric representation based on a Signed Distance Function (SDF) to guide the rendering process. This is complemented by a novel Geometry-Preservation Loss which ensures that fine structural details are preserved. Our framework achieves competitive rendering performance, while demonstrating a 4-5x reduction reduction in energy consumption compared to similar methods. We demonstrate that Geo-NVS-w is a robust method for in-the-wild NVS, yielding photorealistic results with sharp, geometrically coherent details. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08371 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer Tsalakopoulos, Anastasios Kanlis, Angelos Chatzis, Evangelos Karakottas, Antonis Zarpalas, Dimitrios Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning We introduce Geo-NVS-w, a geometry-aware framework for high-fidelity novel view synthesis from unstructured, in-the-wild image collections. While existing in-the-wild methods already excel at novel view synthesis, they often lack geometric grounding on complex surfaces, sometimes producing results that contain inconsistencies. Geo-NVS-w addresses this limitation by leveraging an underlying geometric representation based on a Signed Distance Function (SDF) to guide the rendering process. This is complemented by a novel Geometry-Preservation Loss which ensures that fine structural details are preserved. Our framework achieves competitive rendering performance, while demonstrating a 4-5x reduction reduction in energy consumption compared to similar methods. We demonstrate that Geo-NVS-w is a robust method for in-the-wild NVS, yielding photorealistic results with sharp, geometrically coherent details. |
| title | Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning |
| url | https://arxiv.org/abs/2601.08371 |