Summary of Hi-gan: Hierarchical Inpainting Gan with Auxiliary Inputs For Combined Rgb and Depth Inpainting, by Ankan Dash et al.
HI-GAN: Hierarchical Inpainting GAN with Auxiliary Inputs for Combined RGB and Depth Inpainting
by Ankan Dash, Jingyi Gu, Guiling Wang
First submitted to arxiv on: 15 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers propose a novel approach called Hierarchical Inpainting GAN (HI-GAN) for filling in missing pixels or areas in images. This technique is crucial for Mixed Reality environments, particularly in Diminished Reality where content is removed from the user’s visual environment. The existing methods rely on digital replacement techniques that require multiple cameras and are costly. ToF depth sensors used in AR devices and smartphones capture scene depth maps aligned with RGB images, but they create imperfect depth maps with missing pixels. HI-GAN addresses these challenges by using three GANs in a hierarchical fashion for RGBD inpainting. EdgeGAN and LabelGAN inpaint masked edge and segmentation label images respectively, while CombinedRGBD-GAN combines their latent representation outputs and performs RGB and Depth inpainting. The results show that HI-GAN achieves superior performance compared to existing approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, scientists are working on a way to fix broken images. They want to make it easier to create Mixed Reality environments where things can be removed from the image. Right now, there are special cameras and computers needed to do this, which is expensive. The researchers have come up with a new idea called HI-GAN that uses three different kinds of computer models working together to fix broken images. This makes it faster and cheaper than before. They tested their idea and found that it works better than other ways they tried. |
Keywords
* Artificial intelligence * Gan
