High Dynamic Range Image Tone Mapping Based on Layer Decomposition and Image Fusion
원문 초록
Common displays have limited dynamic range and therefore cannot support direct reproduction of high dynamic range (HDR) images. Generally, this gap can be effectively solved by image tone mapping. One of the typical tone mapping methods is known as layer decomposition based algorithms. They decompose an HDR image into base and detail layers, and reduce the dynamic range by employing gamma functions on the base layer. However, simple gamma curves are not sufficient to produce good local contrasts. This paper proposes a layer decomposition based method by utilizing image fusion techniques to enhance local contrasts. Our method constructs virtual images to stretch dark, normal and bright regions of the base layer respectively and fuses them together for contrast enhancement. Experimental results validate that the proposed method produces enhanced local contrasts and more natural colors in the tone-mapped images.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling
GS-I$^{3}$: Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent Images
Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared images
Deep chroma compression of tone-mapped images
HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images
Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.