태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Denoising is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.
<span style="color:grey; opacity: 0.6">( Image credit: Beyond a Gaussian Denoiser )</span>
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
The Raw Natural Image Noise Dataset (RawNIND) is a diverse collection of paired raw images designed to support the development of denoising models that generalize across sensors, image development workflows, and styles. RawNIND contains 2831 raw images (2279 noisy and 562 clean) split across 310 scenes and 11 cameras.
We propose a new light field image database called “PINet” inheriting the hierarchical structure from WordNet. It consists of 7549 LIs captured by Lytro Illum, which is much larger than the existing databases. The images are manually annotated to 178 categories according to WordNet, such as cat, camel, bottle, fans, etc. The registered depth maps are also provided. Each image is generated by processing the raw LI from the camera by Light Field Toolbox v0.4 for demosaicing and devignetting. PINet is the largest light field image dataset. More details can be found in https://github.com/VincentChandelier/SADN
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.