Point Cloud Color Constancy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2021
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929439157256192 |
|---|---|
| author | Xing, Xiaoyan Qian, Yanlin Feng, Sibo Dong, Yuhan Matas, Jiri |
| author_facet | Xing, Xiaoyan Qian, Yanlin Feng, Sibo Dong, Yuhan Matas, Jiri |
| contents | In this paper, we present Point Cloud Color Constancy, in short PCCC, an illumination chromaticity estimation algorithm exploiting a point cloud. We leverage the depth information captured by the time-of-flight (ToF) sensor mounted rigidly with the RGB sensor, and form a 6D cloud where each point contains the coordinates and RGB intensities, noted as (x,y,z,r,g,b). PCCC applies the PointNet architecture to the color constancy problem, deriving the illumination vector point-wise and then making a global decision about the global illumination chromaticity. On two popular RGB-D datasets, which we extend with illumination information, as well as on a novel benchmark, PCCC obtains lower error than the state-of-the-art algorithms. Our method is simple and fast, requiring merely 16*16-size input and reaching speed over 500 fps, including the cost of building the point cloud and net inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2111_11280 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Point Cloud Color Constancy Xing, Xiaoyan Qian, Yanlin Feng, Sibo Dong, Yuhan Matas, Jiri Computer Vision and Pattern Recognition In this paper, we present Point Cloud Color Constancy, in short PCCC, an illumination chromaticity estimation algorithm exploiting a point cloud. We leverage the depth information captured by the time-of-flight (ToF) sensor mounted rigidly with the RGB sensor, and form a 6D cloud where each point contains the coordinates and RGB intensities, noted as (x,y,z,r,g,b). PCCC applies the PointNet architecture to the color constancy problem, deriving the illumination vector point-wise and then making a global decision about the global illumination chromaticity. On two popular RGB-D datasets, which we extend with illumination information, as well as on a novel benchmark, PCCC obtains lower error than the state-of-the-art algorithms. Our method is simple and fast, requiring merely 16*16-size input and reaching speed over 500 fps, including the cost of building the point cloud and net inference. |
| title | Point Cloud Color Constancy |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2111.11280 |