GANESH: Generalizable NeRF for Lensless Imaging
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913573693816832 |
|---|---|
| author | Madavan, Rakesh Raj Kaimal, Akshat K V, Badhrinarayanan Gupta, Vinayak Choudhary, Rohit Shanmuganathan, Chandrakala Mitra, Kaushik |
| author_facet | Madavan, Rakesh Raj Kaimal, Akshat K V, Badhrinarayanan Gupta, Vinayak Choudhary, Rohit Shanmuganathan, Chandrakala Mitra, Kaushik |
| contents | Lensless imaging offers a significant opportunity to develop ultra-compact cameras by removing the conventional bulky lens system. However, without a focusing element, the sensor's output is no longer a direct image but a complex multiplexed scene representation. Traditional methods have attempted to address this challenge by employing learnable inversions and refinement models, but these methods are primarily designed for 2D reconstruction and do not generalize well to 3D reconstruction. We introduce GANESH, a novel framework designed to enable simultaneous refinement and novel view synthesis from multi-view lensless images. Unlike existing methods that require scene-specific training, our approach supports on-the-fly inference without retraining on each scene. Moreover, our framework allows us to tune our model to specific scenes, enhancing the rendering and refinement quality. To facilitate research in this area, we also present the first multi-view lensless dataset, LenslessScenes. Extensive experiments demonstrate that our method outperforms current approaches in reconstruction accuracy and refinement quality. Code and video results are available at https://rakesh-123-cryp.github.io/Rakesh.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04810 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GANESH: Generalizable NeRF for Lensless Imaging Madavan, Rakesh Raj Kaimal, Akshat K V, Badhrinarayanan Gupta, Vinayak Choudhary, Rohit Shanmuganathan, Chandrakala Mitra, Kaushik Computer Vision and Pattern Recognition Image and Video Processing Lensless imaging offers a significant opportunity to develop ultra-compact cameras by removing the conventional bulky lens system. However, without a focusing element, the sensor's output is no longer a direct image but a complex multiplexed scene representation. Traditional methods have attempted to address this challenge by employing learnable inversions and refinement models, but these methods are primarily designed for 2D reconstruction and do not generalize well to 3D reconstruction. We introduce GANESH, a novel framework designed to enable simultaneous refinement and novel view synthesis from multi-view lensless images. Unlike existing methods that require scene-specific training, our approach supports on-the-fly inference without retraining on each scene. Moreover, our framework allows us to tune our model to specific scenes, enhancing the rendering and refinement quality. To facilitate research in this area, we also present the first multi-view lensless dataset, LenslessScenes. Extensive experiments demonstrate that our method outperforms current approaches in reconstruction accuracy and refinement quality. Code and video results are available at https://rakesh-123-cryp.github.io/Rakesh.github.io/ |
| title | GANESH: Generalizable NeRF for Lensless Imaging |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2411.04810 |