hootoon / MG-Cycle-GANLinks
We convert the highlight removal problem to image-to-image translation by using cycle-consistent adversarial network (Cycle-GAN). The network can remove the specular highlight from natural images.
☆29Updated 2 years ago
Alternatives and similar repositories for MG-Cycle-GAN
Users that are interested in MG-Cycle-GAN are comparing it to the libraries listed below
Sorting:
- ☆43Updated 3 years ago
- Text-Aware Single Image Specular Highlight Removal☆20Updated last year
- [CVPR 2022 Oral] Official implementation for "Discrete Cosine Transform Network for Guided Depth Map Super-Resolution."☆97Updated 3 years ago
- The Offical Codebase for Fully Self-Supervised Depth Estimation from Defocus Clue☆48Updated 2 years ago
- [AAAI 2023] Learning Continuous Depth Representation via Geometric Spatial Aggregator☆29Updated 2 years ago
- Official Pytorch implementation of ICCV 2021 2020 paper "Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervisi…☆49Updated last year
- [ACM MM 2024] Dual-Hybrid Attention Network for Specular Highlight Removal☆24Updated 3 months ago
- ☆44Updated 4 years ago
- [TCSVT 2022] UrbanLF: A Comprehensive Light Field Dataset for Semantic Segmentation of Urban Scenes☆26Updated last year
- Deep Attentional Guided Image Filtering, Winner solution for ICMR 2021 Real DSR Challenge (IEEE TNNLS 2023)☆28Updated 2 months ago
- PyTorch implementation of KPA-Flow. Learning Optical Flow with Kernel Patch Attention (CVPR-2022)☆45Updated 3 years ago
- [CVPR 2022] Occlusion-Aware Cost Constructor for Light Field Depth Estimation☆63Updated 3 years ago
- This is the official implementation of HomoGAN, CVPR2022