A Benchmark for Temporal Color Constancy
원문 초록
Temporal Color Constancy (CC) is a recently proposed approach that challenges the conventional single-frame color constancy. The conventional approach is to use a single frame - shot frame - to estimate the scene illumination color. In temporal CC, multiple frames from the view finder sequence are used to estimate the color. However, there are no realistic large scale temporal color constancy datasets for method evaluation. In this work, a new temporal CC benchmark is introduced. The benchmark comprises of (1) 600 real-world sequences recorded with a high-resolution mobile phone camera, (2) a fixed train-test split which ensures consistent evaluation, and (3) a baseline method which achieves high accuracy in the new benchmark and the dataset used in previous works. Results for more than 20 well-known color constancy methods including the recent state-of-the-arts are reported in our experiments.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Colorful Diffuse Intrinsic Image Decomposition in the Wild
Lesion Elevation Prediction from Skin Images Improves Diagnosis
Simple Image Signal Processing using Global Context Guidance
Self-Supervised Learning of Color Constancy
Pixel-Wise Color Constancy via Smoothness Techniques in Multi-Illuminant Scenes
Model-Based Image Signal Processors via Learnable Dictionaries
토론
이 논문과 연결된 포럼 글이 아직 없습니다.