Deep Learning

Hello everyone, regard the topic for our project in course (Braude college), we choose the topic: GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior. link: https://mane-aajay.medium.com/gfp-gan-towards-real-world-blind-face-restoration-with-generative-facial-prior-5db

Hi Tomer! Me and Natalie wish to do the project on this topic: https://arxiv.org/abs/1812.11006 hope it's ok. Have a great weekend, Sivan

hey tomer, me and Shay would like to do our project on this topic. Facebook AI Introduces A New Image Generation Model Called 'IC GAN' That Creates High Quality Images,https://www.youtube.com/watch?v=v074LrVQt0w&t=4s if this topic is unavailable, we would like to do on CycleGAN for image-to-image t

hello tomer, me (tomer) and my partner ohad natan would like to present about the paper in this link: https://paperswithcode.com/paper/adversarial-audio-synthesis

Eden Attias & Shmual shaul

Hi Tomer, me (Matar) and my partner Bar would like to present the paper in this link: https://openaccess.thecvf.com/content/CVPR2022/papers/Wu_HairMapper_Removing_Hair_From_Portraits_Using_GANs_CVPR_2022_paper.pdf This is a video about this paper: HairMapper: Removing Hair from Portraits Using

Hi Tomer, My name is Boris Lasker and my partner Daniel Khait we would like to make our project about this video.

Hi tomer, Dor and i (Aviv) choose to present the paper in this video: This Magical AI Cuts People Out Of Your Videos! ✂️,https://www.youtube.com/watch?v=lCBSGOwV-_o Thanks, Aviv and Dor.

Hi tomer, Liad and I have a few subjects for the project in order of preference. 1. 3D Photography using Context-aware Layered Depth Inpainting https://arxiv.org/abs/2004.04727 2. ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement https://arxiv.org/abs/2104.02699 3. Image Super-

Hi Tomer, Gefen and I would like to present the paper in this video: Deformable Style Transfer (ECCV 2020) - 10min Talk,https://www.youtube.com/watch?v=mVU5tSxS4is&ab_channel=SunnieS.Y.Kim Link to the paper: https://sunniesuhyoung.github.io/DST-page/ We would like to present on 4.1.2021 Thank yo

שלום תומר שמי אופק והשותף שלי אלדד מצאנו כמה נושאים לפרוייקט. שלושת הנושאים מסודרים לפי סדר העדיפויות: StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery This AI Made Me Look Like Obi-Wan Kenobi! 🧔,https://www.youtube.com/watch?v=yc1WpkthV3g Editable Free-Viewpoint Video using a Layered N

Hey Tomer, me and Bar Firuan would like to explore the mentioned subject for the course project. it is a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. Thanks! Gi

Hi Tomer, Noy Zimmer and i would like to present the paper in this video: Deep Photo Style Transfer | Two Minute Papers #150,https://www.youtube.com/watch?v=HTUxsrO-P_8&ab_channel=TwoMinutePapers we would like to present our project on 04/01/2022 thank you.

Hi Tomer, we would like to present the paper in this video: https://www.youtube.com/watch?v=zDTUbtmUbG8 (This AI Makes Celebrities Old…For a Price! 👵) Code: https://yuval-alaluf.github.io/SAM/ Students: Bshara Zahran, Roy Atali Thanks, Bshara

Hello Tomer, I'm willing to present about "Colorization of Black and White Images Using Deep Learning". an article that was published in Oct 2021. I'm looking forward to your approval. Link to the research

Hi Tomer, Me and Rostislav would like to present 'Masked Autoencoders Are Scalable Vision Learners ': https://arxiv.org/abs/2111.06377

Hi Tomer, My partner Ruslan Abd El-Rahman and I would like to prepare a presentation on UnfairGAN Paper: https://paperswithcode.com/paper/unfairgan-an-enhanced-generative-adversarial Regards, Murad Eissa

Hi Tomer, Me and my partner Andi, would like to present the following paper about "BART Denoising Sequence-to-Sequence Pre-training for Natural" Article description: BART performs natural language generation, comprehension, and translation tasks by using noising transformations for pre-training,

Hi Tomer, We (Evgeny and Saar) would like to present the paper in this link: https://aclanthology.org/2020.acl-main.31.pdf

Hi Tomer, My partner Moran Levi and I would like to prepare a presentation on DreamFusion: Text-to-3D using 2D Diffusion. Paper: https://paperswithcode.com/paper/dreamfusion-text-to-3d-using-2d-diffusion YouTube: https://www.youtube.com/watch?v=L3G0dx1Q0R8 Regards, Ayala Cohen

Hello, Sapir and I(Haim) would like to present paper about generate realistic image from text using BERT + STACKGAN link to the pdf: https://arxiv.org/pdf/1612.03242.pdf In the paper there are text description of a bird for an example, and from its description we produce a composite image that t

transforming real-life photos to cartoons by 2 CNN discriminator and generator approaches, Generative adversarial network is a class of machine learning frameworks. suggested by khalil daibes and saeed ismael. https://cartoonify.netlify.app/ https://github.com/ahmedbesbes/cartoonify/

Hey Tomer, I would like to present the paper: "Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data". Link: https://arxiv.org/pdf/2107.10833v2.pdf But I saw that bradley.fe2015 has already posted he want to do his project on this paper. Is there a chance that I can pres

High-Resolution Daytime Translation Without Domain Labels: https://arxiv.org/pdf/2003.08791.pdf Yossi Gelman Eldan menahem This AI Creates Beautiful Time Lapse Videos ☀️,https://www.youtube.com/watch?v=EWKAgwgqXB4

Hi Tomer! Lior Kauffman and I chose this subject: Style-Based Age Manipulation. you already approved it to Lior by email. thanks!

hi tomer we would like to choose the Deep Single-Image Portrait Relighting project . yossi gelman el-dan menahem https://www.youtube.com/watch?v=Ks7wDYsN4yM

Hi, Dana and I decided to do about Instance aware image colorization link: https://www.youtube.com/watch?v=2wcw_O_19XQ&list=PUbfYPyITQ-7l4upoX8nvctg&index=17

היי תומר יש לנו שני נושאים לפרויקט ונשמח לשמוע את דעתך: 1)יש פרוייקט שחבר'ה במכללה עשו, פרוייקט סוף מדהים לזיהוי תסמיני מחלה הנקראת לרינגופרינגל. הם לקחו דאטא אמיתי מבתי חולים והתייעצו עם רופאים כדי להגדיר ולסווג את התסמינים. פרויקט זה משתמש ביולו 3, עם תמונות אמיתיות של חולים ועם labeling לתמונות