paper-with-me

홈 › Papers

Intrinsic Image Harmonization

2021-06-19 · CVPR 2021 1 · Zonghui Guo, Haiyong Zheng, Yufeng Jiang, Zhaorui Gu, Bing Zheng

Compositing an image usually inevitably suffers from inharmony problem that is mainly caused by incompatibility of foreground and background from two different images with distinct surfaces and lights, corresponding to material-dependent and light-dependent characteristics, namely, reflectance and illumination intrinsic images, respectively. Therefore, we seek to solve image harmonization via separable harmonization of reflectance and illumination, i.e., intrinsic image harmonization. Our method is based on an autoencoder that disentangles composite image into reflectance and illumination for further separate harmonization. Specifically, we harmonize reflectance through material-consistency penalty, while harmonize illumination by learning and transferring light from background to foreground, moreover, we model patch relations between foreground and background of composite images in an inharmony-free learning way, to adaptively guide our intrinsic image harmonization. Both extensive experiments and ablation studies demonstrate the power of our method as well as the efficacy of each component. We also contribute a new challenging dataset for benchmarking illumination harmonization. Code and dataset are at https://github.com/zhenglab/IntrinsicHarmony.

📄 PDF Abstract BibTeX

Code (1)

zhenglab/IntrinsicHarmony 공식 구현 pytorch

Tasks

BenchmarkingImage Harmonization

Similar Papers 제목 키워드 기반

Intrinsic Harmonization for Illumination-Aware Compositing

2023-12-06 · Chris Careaga, S. Mahdi H. Miangoleh, Yağız Aksoy

Despite significant advancements in network-based image harmonization techniques, there still exists a domain disparity between typical training pairs and real-world composites encountered during inference. Most existing…

Image HarmonizationImage Relighting

Multimodal Gaussian Process Latent Variable Models With Harmonization

2017-10-01 · ICCV 2017 10 · Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian

In this work, we address multimodal learning problem with Gaussian process latent variable models (GPLVMs) and their application to cross-modal retrieval. Existing GPLVM based studies generally impose individual priors o…

Cross-Modal RetrievalRetrieval

Quantitative Metrics for Benchmarking Medical Image Harmonization

2024-02-06 · Abhijeet Parida, Zhifan Jiang, Roger J. Packer, Robert A. Avery 외

Image harmonization is an important preprocessing strategy to address domain shifts arising from data acquired using different machines and scanning protocols in medical imaging. However, benchmarking the effectiveness o…

AnatomyBenchmarkingImage HarmonizationImage Quality Assessment

Interactive Portrait Harmonization

2022-03-15 · Jeya Maria Jose Valanarasu, He Zhang, Jianming Zhang, Yilin Wang 외

Current image harmonization methods consider the entire background as the guidance for harmonization. However, this may limit the capability for user to choose any specific object/person in the background to guide the ha…

Image Harmonization

Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night

2019-08-28 · Wenyan Cong, Jianfu Zhang, Li Niu, Liu Liu 외

Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image. Image harmonization, which aims to make the …

DiversityImage Harmonization