Specularity Factorization for Low-Light Enhancement
S Saini, PJ Narayanan - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
We present a new additive image factorization technique that treats images to be composed
of multiple latent specular components which can be simply estimated recursively by …
of multiple latent specular components which can be simply estimated recursively by …
Interpreting intrinsic image decomposition using concept activations
Evaluation of ill-posed problems like Intrinsic Image Decomposition (IID) is challenging. IID
involves decomposing an image into its constituent illumination-invariant Reflectance (R) …
involves decomposing an image into its constituent illumination-invariant Reflectance (R) …
Quaternion Factorized Simulated Exposure Fusion
S Saini, PJ Narayanan - … of the Thirteenth Indian Conference on …, 2022 - dl.acm.org
Image Fusion maximizes the visual information at each pixel location by merging content
from multiple images in order to produce an enhanced image. Exposure Fusion, specifically …
from multiple images in order to produce an enhanced image. Exposure Fusion, specifically …
Semantic hierarchical priors for intrinsic image decomposition
S Saini, PJ Narayanan - arXiv preprint arXiv:1902.03830, 2019 - arxiv.org
Intrinsic Image Decomposition (IID) is a challenging and interesting computer vision problem
with various applications in several fields. We present novel semantic priors and an …
with various applications in several fields. We present novel semantic priors and an …