Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2401.09126 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929313048166400 |
|---|---|
| author | Ummenhofer, Benjamin Agrawal, Sanskar Sepulveda, Rene Lao, Yixing Zhang, Kai Cheng, Tianhang Richter, Stephan Wang, Shenlong Ros, German |
| author_facet | Ummenhofer, Benjamin Agrawal, Sanskar Sepulveda, Rene Lao, Yixing Zhang, Kai Cheng, Tianhang Richter, Stephan Wang, Shenlong Ros, German |
| contents | Reconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also to the new lighting conditions and yet evaluations of inverse rendering methods rely on novel view synthesis data or simplistic synthetic datasets for quantitative analysis. This work presents a real-world dataset for measuring the reconstruction and rendering of objects for relighting. To this end, we capture the environment lighting and ground truth images of the same objects in multiple environments allowing to reconstruct the objects from images taken in one environment and quantify the quality of the rendered views for the unseen lighting environments. Further, we introduce a simple baseline composed of off-the-shelf methods and test several state-of-the-art methods on the relighting task and show that novel view synthesis is not a reliable proxy to measure performance. Code and dataset are available at https://github.com/isl-org/objects-with-lighting . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09126 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting Ummenhofer, Benjamin Agrawal, Sanskar Sepulveda, Rene Lao, Yixing Zhang, Kai Cheng, Tianhang Richter, Stephan Wang, Shenlong Ros, German Computer Vision and Pattern Recognition Graphics Reconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also to the new lighting conditions and yet evaluations of inverse rendering methods rely on novel view synthesis data or simplistic synthetic datasets for quantitative analysis. This work presents a real-world dataset for measuring the reconstruction and rendering of objects for relighting. To this end, we capture the environment lighting and ground truth images of the same objects in multiple environments allowing to reconstruct the objects from images taken in one environment and quantify the quality of the rendered views for the unseen lighting environments. Further, we introduce a simple baseline composed of off-the-shelf methods and test several state-of-the-art methods on the relighting task and show that novel view synthesis is not a reliable proxy to measure performance. Code and dataset are available at https://github.com/isl-org/objects-with-lighting . |
| title | Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2401.09126 |