Heng Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Heng Guo has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Boxin Shi
Peking University, Beijing, China
2 shared publications - Fumio Okura
The University of Osaka
1 shared publication - Guanying Chen
School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China
1 shared publication - Jiani Hu
Beijing University of Posts and Telecommunications
1 shared publication Jinxiu Liang
Peking University
1 shared publication- Jipeng Lyu
Peking University
1 shared publication
Latest Publications
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4515-4523
Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
Face super-resolution aims to reconstruct a high-resolution face image from a low-resolution face image. Previous methods typically employ an encoder-decoder structure to extract facial structural features, where the direct downsampling inevitably introduces distortions, especially to high-frequency features such as edges. To address this issue, we propose a wavelet-based feature enhancement network, which mitigates feature distortion by losslessly decomposing the input feature into high and low-frequency components using the wavelet transform and processing them separately. To improve the efficiency of facial feature extraction, a full domain Transformer is further proposed to enhance local, regional, and global facial features. Such designs allow our method to perform better without stacking many modules as previous methods did. Experiments show that our method effectively balances performance, model size, and speed. Code link: https://github.com/PRIS-CV/WFEN.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4515-4523
Open AccessEfficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
Face super-resolution aims to reconstruct a high-resolution face image from a low-resolution face image. Previous methods typically employ an encoder-decoder structure to extract facial structural features, where the direct downsampling inevitably introduces distortions, especially to high-frequency features such as edges. To address this issue, we propose a wavelet-based feature enhancement network, which mitigates feature distortion by losslessly decomposing the input feature into high and low-frequency components using the wavelet transform and processing them separately. To improve the efficiency of facial feature extraction, a full domain Transformer is further proposed to enhance local, regional, and global facial features. Such designs allow our method to perform better without stacking many modules as previous methods did. Experiments show that our method effectively balances performance, model size, and speed. Code link: https://github.com/PRIS-CV/WFEN.
- Open Access
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1249-1257
Non-Lambertian Multispectral Photometric Stereo via Spectral Reflectance Decomposition
Multispectral photometric stereo (MPS) aims at recovering the surface normal of a scene from a single-shot multispectral image captured under multispectral illuminations. Existing MPS methods adopt the Lambertian reflectance model to make the problem tractable, but it greatly limits their application to real-world surfaces. In this paper, we propose a deep neural network named NeuralMPS to solve the MPS problem under non-Lambertian spectral reflectances. Specifically, we present a spectral reflectance decomposition model to disentangle the spectral reflectance into a geometric component and a spectral component. With this decomposition, we show that the MPS problem for surfaces with a uniform material is equivalent to the conventional photometric stereo (CPS) with unknown light intensities. In this way, NeuralMPS reduces the difficulty of the non-Lambertian MPS problem by leveraging the well-studied non-Lambertian CPS methods. Experiments on both synthetic and real-world scenes demonstrate the effectiveness of our method.
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1249-1257
Open AccessNon-Lambertian Multispectral Photometric Stereo via Spectral Reflectance Decomposition
Multispectral photometric stereo (MPS) aims at recovering the surface normal of a scene from a single-shot multispectral image captured under multispectral illuminations. Existing MPS methods adopt the Lambertian reflectance model to make the problem tractable, but it greatly limits their application to real-world surfaces. In this paper, we propose a deep neural network named NeuralMPS to solve the MPS problem under non-Lambertian spectral reflectances. Specifically, we present a spectral reflectance decomposition model to disentangle the spectral reflectance into a geometric component and a spectral component. With this decomposition, we show that the MPS problem for surfaces with a uniform material is equivalent to the conventional photometric stereo (CPS) with unknown light intensities. In this way, NeuralMPS reduces the difficulty of the non-Lambertian MPS problem by leveraging the well-studied non-Lambertian CPS methods. Experiments on both synthetic and real-world scenes demonstrate the effectiveness of our method.
- 6 July 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (9) , 2166-2183
Multispectral Photometric Stereo for Spatially-Varying Spectral Reflectances
- 6 July 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (9) , 2166-2183
Multispectral Photometric Stereo for Spatially-Varying Spectral Reflectances