Ziyuan Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ziyuan Li has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chenlin Meng
Stanford University
1 shared publication - Gengchen Mai
SEAI Lab, Department of Geography and the Environment, University of Texas at Austin, Austin, TX, USA
1 shared publication - Hongxu Ma
Alphabet Inc
1 shared publication - Jiaming Song
Department of Computer Science Stanford University
1 shared publication - Jinmeng Rao
Google Deepmind Google Deepmind Google Deepmind Google Research
1 shared publication - Ni Lao
SEAI Lab, University of Texas at Austin
1 shared publication
Latest Publications
- Open Access
SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution
Existing digital sensors capture images at fixed spatial and spectral resolutions (e.g., RGB, multispectral, and hyperspectral images), and each combination requires bespoke machine learning models. Neural Implicit Functions partially overcome the spatial resolution challenge by representing an image in a resolution-independent way. However, they still operate at fixed, pre-defined spectral resolutions. To address this challenge, we propose Spatial-Spectral Implicit Function (SSIF), a neural implicit model that represents an image as a function of both continuous pixel coordinates in the spatial domain and continuous wavelengths in the spectral domain. We empirically demonstrate the effectiveness of SSIF on two challenging spatio-spectral super-resolution benchmarks. We observe that SSIF consistently outperforms state-of-the-art baselines even when the baselines are allowed to train separate models at each spectral resolution. We show that SSIF generalizes well to both unseen spatial resolutions and spectral resolutions. Moreover, SSIF can generate high-resolution images that improve the performance of downstream tasks (e.g., land use classification) by 1.7%-7%.
Open AccessSSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution
Existing digital sensors capture images at fixed spatial and spectral resolutions (e.g., RGB, multispectral, and hyperspectral images), and each combination requires bespoke machine learning models. Neural Implicit Functions partially overcome the spatial resolution challenge by representing an image in a resolution-independent way. However, they still operate at fixed, pre-defined spectral resolutions. To address this challenge, we propose Spatial-Spectral Implicit Function (SSIF), a neural implicit model that represents an image as a function of both continuous pixel coordinates in the spatial domain and continuous wavelengths in the spectral domain. We empirically demonstrate the effectiveness of SSIF on two challenging spatio-spectral super-resolution benchmarks. We observe that SSIF consistently outperforms state-of-the-art baselines even when the baselines are allowed to train separate models at each spectral resolution. We show that SSIF generalizes well to both unseen spatial resolutions and spectral resolutions. Moreover, SSIF can generate high-resolution images that improve the performance of downstream tasks (e.g., land use classification) by 1.7%-7%.