Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929227642699776 |
|---|---|
| author | Ramirez, Pierluigi Zama Costanzino, Alex Tosi, Fabio Poggi, Matteo Salti, Samuele Mattoccia, Stefano Di Stefano, Luigi |
| author_facet | Ramirez, Pierluigi Zama Costanzino, Alex Tosi, Fabio Poggi, Matteo Salti, Samuele Mattoccia, Stefano Di Stefano, Luigi |
| contents | Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open in this field: dealing with non-Lambertian materials and effectively processing high-resolution images. Purposely, we propose a novel dataset that includes accurate and dense ground-truth labels at high resolution, featuring scenes containing several specular and transparent surfaces. Our acquisition pipeline leverages a novel deep space-time stereo framework, enabling easy and accurate labeling with sub-pixel precision. The dataset is composed of 606 samples collected in 85 different scenes, each sample includes both a high-resolution pair (12 Mpx) as well as an unbalanced stereo pair (Left: 12 Mpx, Right: 1.1 Mpx), typical of modern mobile devices that mount sensors with different resolutions. Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. The dataset is composed of a train set and two test sets, the latter devoted to the evaluation of stereo and monocular depth estimation networks. Our experiments highlight the open challenges and future research directions in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_08245 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces Ramirez, Pierluigi Zama Costanzino, Alex Tosi, Fabio Poggi, Matteo Salti, Samuele Mattoccia, Stefano Di Stefano, Luigi Computer Vision and Pattern Recognition Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open in this field: dealing with non-Lambertian materials and effectively processing high-resolution images. Purposely, we propose a novel dataset that includes accurate and dense ground-truth labels at high resolution, featuring scenes containing several specular and transparent surfaces. Our acquisition pipeline leverages a novel deep space-time stereo framework, enabling easy and accurate labeling with sub-pixel precision. The dataset is composed of 606 samples collected in 85 different scenes, each sample includes both a high-resolution pair (12 Mpx) as well as an unbalanced stereo pair (Left: 12 Mpx, Right: 1.1 Mpx), typical of modern mobile devices that mount sensors with different resolutions. Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. The dataset is composed of a train set and two test sets, the latter devoted to the evaluation of stereo and monocular depth estimation networks. Our experiments highlight the open challenges and future research directions in this field. |
| title | Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2301.08245 |