What is the space of camera response functions?
By M. Grossberg, Shree K. Nayar. 2003
215 citations recorded by the source corpus.
Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Atomic and Molecular Physics, and Optics
- Radu Timofte
- Yuki Endo
- Yoshihiro Kanamori
- Jun Mitani
- Luc Van Gool
- Kai Zhang
- Rynson W. H. Lau
- Kurt Debattista
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Radu Timofte
- Ming-Hsuan Yang
- Chen Change Loy
- Dacheng Tao
- Andrew Zisserman
- Kai Zhang
- Bernt Schiele
Citations in the corpus
- Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, methodology): “For the tone mapping, we manually select the best fitted tone curve from [14] for each camera based on paired raw image files and the RGB output.”
- Deep reverse tone mapping (2017, methodology): “To define CRFs, we use Grossberg and Nayar’s Database of Response Functions (DoRF) [Grossberg and Nayar 2003].”
- Learning to Restore Low-Light Images via Decomposition-and-Enhancement (2020, methodology): “As the non-linearity introduced by the camera response function varies across cameras and is difficult to reverse-engineer [17], we apply the gamma function as the de-linearization function, as suggested in [12].”
- ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content (2018, methodology): “Following the Deep Reverse Tone Mapping [EKM17], the same database of CRFs was used [GN03], and the same method of obtaining five representative CRFs by k-means clustering was adopted.”
- Modeling the space of camera response functions (2004, background): “Part of this work has appeared in [14].”
- Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs (2019, methodology): “During training, we further augment the dataset with standard cropping and image processing primitives, and also a few specialized ones: modelling camera sensor noise [8] and applying a randomized non-linear parametric transformation to the image intensity histogram (the latter helps simulating marg”
- HDR image reconstruction from a single exposure using deep CNNs (2017, methodology): “Although a sigmoid function fits well with camera curves in general [Grossberg and Nayar 2003], its inverse is not continuous over IR + .”
- Color lines: image specific color representation (2004, background): “An extensive survey on the subject can be found in [6].”