paper-with-me

홈 › Papers

Deep Single-Image Portrait Relighting

2019-10-01 · ICCV 2019 10 · Hao Zhou, Sunil Hadap, Kalyan Sunkavalli, David W. Jacobs

Conventional physically-based methods for relighting portrait images need to solve an inverse rendering problem, estimating face geometry, reflectance and lighting. However, the inaccurate estimation of face components can cause strong artifacts in relighting, leading to unsatisfactory results. In this work, we apply a physically-based portrait relighting method to generate a large scale, high quality, "in the wild" portrait relighting dataset (DPR). A deep Convolutional Neural Network (CNN) is then trained using this dataset to generate a relit portrait image by using a source image and a target lighting as input. The training procedure regularizes the generated results, removing the artifacts caused by physically-based relighting methods. A GAN loss is further applied to improve the quality of the relit portrait image. Our trained network can relight portrait images with resolutions as high as 1024 x 1024. We evaluate the proposed method on the proposed DPR datset, Flickr portrait dataset and Multi-PIE dataset both qualitatively and quantitatively. Our experiments demonstrate that the proposed method achieves state-of-the-art results. Please refer to https://zhhoper.github.io/dpr.html for dataset and code.

📄 PDF Abstract BibTeX

Code (1)

zhhoper/DPR 공식 구현 pytorch

Tasks

Inverse RenderingSingle-Image Portrait Relighting

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Text2Relight: Creative Portrait Relighting with Text Guidance

2024-12-18 · Junuk Cha, Mengwei Ren, Krishna Kumar Singh, He Zhang 외

We present a lighting-aware image editing pipeline that, given a portrait image and a text prompt, performs single image relighting. Our model modifies the lighting and color of both the foreground and background to alig…

Image GenerationImage RelightingLarge Language Model

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

2024-03-14 · CVPR 2024 1 · Yiqun Mei, Yu Zeng, He Zhang, Zhixin Shu 외

At the core of portrait photography is the search for ideal lighting and viewpoint. The process often requires advanced knowledge in photography and an elaborate studio setup. In this work, we propose Holo-Relighting, a …

Single Image Portrait Relighting

2019-05-02 · Tiancheng Sun, Jonathan T. Barron, Yun-Ta Tsai, Zexiang Xu 외

Lighting plays a central role in conveying the essence and depth of the subject in a portrait photograph. Professional photographers will carefully control the lighting in their studio to manipulate the appearance of the…

Single-Image Portrait Relighting

Lite2Relight: 3D-aware Single Image Portrait Relighting

2024-07-15 · Pramod Rao, Gereon Fox, Abhimitra Meka, Mallikarjun B R 외

Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of gene…

Single-Image Portrait Relighting

Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation

2022-09-21 · Yu-Ying Yeh, Koki Nagano, Sameh Khamis, Jan Kautz 외

Given a portrait image of a person and an environment map of the target lighting, portrait relighting aims to re-illuminate the person in the image as if the person appeared in an environment with the target lighting. To…