5 papers
Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation
Sangmin Han, Jinho Kim, Jinwoo Kim +2
Multi-exposure fusion (MEF) expands the luminance range beyond what a single exposure can capture. Combining images taken at different exposure levels requires handling geometric d…
RawGen: Learning Camera Raw Image Generation
Dongyoung Kim, Junyong Lee, Abhijith Punnappurath +4
Cameras capture scene-referred linear raw images, which are processed by onboard image signal processors (ISPs) into display-referred 8-bit sRGB outputs. Although raw data is more…
CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy
Dongyoung Kim, Mahmoud Afifi, Dongyun Kim +2
Computational color constancy, or white balancing, is a key module in a camera's image signal processor (ISP) that corrects color casts from scene lighting. Because this operation…
ORIDa: Object-centric Real-world Image Composition Dataset
Jinwoo Kim, Sangmin Han, Jinho Jeong +3
Object compositing, the task of placing and harmonizing objects in images of diverse visual scenes, has become an important task in computer vision with the rise of generative mode…
ATTIQA: Generalizable Image Quality Feature Extractor using Attribute-aware Pretraining
Daekyu Kwon, Dongyoung Kim, Sehwan Ki +3
In no-reference image quality assessment (NR-IQA), the challenge of limited dataset sizes hampers the development of robust and generalizable models. Conventional methods address t…