Neural fields in visual computing and beyond

Y Xie, T Takikawa, S Saito, O Litany… - Computer Graphics …, 2022 - Wiley Online Library
Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …

Image-to-image translation: Methods and applications

Y Pang, J Lin, T Qin, Z Chen - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
Image-to-image translation (I2I) aims to transfer images from a source domain to a target
domain while preserving the content representations. I2I has drawn increasing attention and …

[HTML][HTML] Unsupervised image-to-image translation: A review

H Hoyez, C Schockaert, J Rambach, B Mirbach… - Sensors, 2022 - mdpi.com
Supervised image-to-image translation has been proven to generate realistic images with
sharp details and to have good quantitative performance. Such methods are trained on a …

Gan compression: Efficient architectures for interactive conditional gans

M Li, J Lin, Y Ding, Z Liu, JY Zhu… - Proceedings of the …, 2020 - openaccess.thecvf.com
Abstract Conditional Generative Adversarial Networks (cGANs) have enabled controllable
image synthesis for many computer vision and graphics applications. However, recent …

Efficient spatially sparse inference for conditional gans and diffusion models

M Li, J Lin, C Meng, S Ermon… - Advances in neural …, 2022 - proceedings.neurips.cc
During image editing, existing deep generative models tend to re-synthesize the entire
output from scratch, including the unedited regions. This leads to a significant waste of …

Any-resolution training for high-resolution image synthesis

L Chai, M Gharbi, E Shechtman, P Isola… - European Conference on …, 2022 - Springer
Generative models operate at fixed resolution, even though natural images come in a variety
of sizes. As high-resolution details are downsampled away and low-resolution images are …

Implicit neural spatial representations for time-dependent pdes

H Chen, R Wu, E Grinspun, C Zheng… - … on Machine Learning, 2023 - proceedings.mlr.press
Abstract Implicit Neural Spatial Representation (INSR) has emerged as an effective
representation of spatially-dependent vector fields. This work explores solving time …

High quality segmentation for ultra high-resolution images

T Shen, Y Zhang, L Qi, J Kuen, X Xie… - Proceedings of the …, 2022 - openaccess.thecvf.com
To segment 4K or 6K ultra high-resolution images needs extra computation consideration in
image segmentation. Common strategies, such as down-sampling, patch cropping, and …

Coordfill: Efficient high-resolution image inpainting via parameterized coordinate querying

W Liu, X Cun, CM Pun, M Xia, Y Zhang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Image inpainting aims to fill the missing hole of the input. It is hard to solve this task
efficiently when facing high-resolution images due to two reasons:(1) Large reception field …

Implicit neural representation learning for hyperspectral image super-resolution

K Zhang, D Zhu, X Min, G Zhai - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Hyperspectral image (HSI) super-resolution (SR) without additional auxiliary image remains
a constant challenge due to its high-dimensional spectral patterns, where learning an …