CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918526700224512 |
|---|---|
| author | Polianskii, Vladislav Dima, Elijs Marazuela, Isabel Salmerón Nagy, Gergő László Sverrisson, Sigurdur Grancharov, Volodya |
| author_facet | Polianskii, Vladislav Dima, Elijs Marazuela, Isabel Salmerón Nagy, Gergő László Sverrisson, Sigurdur Grancharov, Volodya |
| contents | Many real-world 3D reconstruction applications demand photorealism and metric accuracy across unbounded, complex scenes with challenging lighting and imperfect captures that current Neural Radiance Field (NeRF) pipelines only partly satisfy. This study adapts NeRF-based 3D reconstruction to multi-region of interest unbounded scenes to improve robustness to lighting and pose variation while enforcing metric accuracy suitable for digital-twin applications. Our approach introduces (i) automated local region localization/detection and reconstruction to seamlessly prioritize areas of interest without proliferating submodules, (ii) collinearity-enforcing ray sampling to learn smooth planar and curved surfaces, (iii) depth-localized neighborhood point extraction to suppress surface artifacts, and (iv) geometry-relevant color aggregation to mitigate lighting- and pose-caused variations. Results indicate superior performance of the proposed pipeline over the baseline NeRF models and established Structure from Motion (SfM) - Multi-View Stereo (MVS) solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28125 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes Polianskii, Vladislav Dima, Elijs Marazuela, Isabel Salmerón Nagy, Gergő László Sverrisson, Sigurdur Grancharov, Volodya Computer Vision and Pattern Recognition Graphics Many real-world 3D reconstruction applications demand photorealism and metric accuracy across unbounded, complex scenes with challenging lighting and imperfect captures that current Neural Radiance Field (NeRF) pipelines only partly satisfy. This study adapts NeRF-based 3D reconstruction to multi-region of interest unbounded scenes to improve robustness to lighting and pose variation while enforcing metric accuracy suitable for digital-twin applications. Our approach introduces (i) automated local region localization/detection and reconstruction to seamlessly prioritize areas of interest without proliferating submodules, (ii) collinearity-enforcing ray sampling to learn smooth planar and curved surfaces, (iii) depth-localized neighborhood point extraction to suppress surface artifacts, and (iv) geometry-relevant color aggregation to mitigate lighting- and pose-caused variations. Results indicate superior performance of the proposed pipeline over the baseline NeRF models and established Structure from Motion (SfM) - Multi-View Stereo (MVS) solutions. |
| title | CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2605.28125 |