@kemelmi Profile picture

ira kemelmacher

@kemelmi

Joined January 2008
Similar User
Andreas Geiger photo

@andreasgeiger0

Angjoo Kanazawa photo

@akanazawa

Sanja Fidler photo

@FidlerSanja

Noah Snavely photo

@Jimantha

Visual Geometry Group (VGG) photo

@Oxford_VGG

Georgia Gkioxari photo

@georgiagkioxari

Angela Dai photo

@angelaqdai

Jun-Yan Zhu photo

@junyanz89

Phillip Isola photo

@phillip_isola

Vittorio Ferrari photo

@VittoFerrariCV

Richard Zhang photo

@rzhang88

Devi Parikh photo

@deviparikh

Rana Hanocka photo

@RanaHanocka

Sergey Tulyakov photo

@SergeyTulyakov

Ben Poole photo

@poolio

Pinned

We’re hiring at Google in generative media (images videos). contact me directly if you’re interested with your cv, relevant work and interests. #cvpr retweets appreciated! #diffusion #imagen #parti #GenerativeAI


ira kemelmacher Reposted

Generative Inbetweening Adapting Image-to-Video Models for Keyframe Interpolation discuss: huggingface.co/papers/2408.15… We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video…

Tweet Image 1

ira kemelmacher Reposted

Last year, we launched virtual try-on for men's and women's shirts, letting you preview every detail — down to shadows and draping — of an item using AI. Now, we're expanding it to include dresses in sizes XXS to XXXL. 👗 Learn more ↓ goo.gle/3AUFpsf


ira kemelmacher Reposted

It’s almost time to say goodbye to 2023 — but first, let’s take a look back at 23 of our biggest moments in 2023 ↓ goo.gle/48pxP4f


ira kemelmacher Reposted

Excited to share our work Generative Powers of Ten w/ @holynski_ @_pratul_ @BenMildenhall @dorverbin @kemelmi Given a set of prompts describing a scene at varying zoom levels, our method creates a seamless zooming video. Check it out here: powers-of-10.github.io


ira kemelmacher Reposted

2/ We’re improving the shopping experience with updates to generative AI in Search, with AI-generated gift recommendations, expanding our virtual try-on feature + a way to generate images and shop products that match. blog.google/products/shopp…


ira kemelmacher Reposted

Excited to share our work on Spatial Audio, presented at #UIST23 🎧 Our neural net uses everyday earbud recordings to create a personalized HRTF, elevating your spatial audio experiences! Explore our findings below Website: grail.cs.washington.edu/projects/hrtf-… Paper: arxiv.org/pdf/2311.03560…


ira kemelmacher Reposted

Excited to share our #ICCV2023 paper with @holynski, @tcwang0509, @kemelmi: “DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion”! Given a still image of a person in a garment and a pose sequence, DreamPose generates a photorealistic video of the person.


ira kemelmacher Reposted

Our new virtual try-on feature uses a technique called diffusion to show you what clothes look like on a wide range of people. Learn more about the tech that's making it easier for you to get a better sense of what clothes will look like on you → goo.gle/466MIIo


ira kemelmacher Reposted

TryOnDiffusion: A Tale of Two UNets paper page: huggingface.co/papers/2306.08… Given two images depicting a person and a garment worn by another person, our goal is to generate a visualization of how the garment might look on the input person. A key challenge is to synthesize a…


ira kemelmacher Reposted

NeRFs on Google Search 🤯! When you look for *shoes* on google.com, you can now find interactive 360 spins for some items generated using NeRFs! These are reconstructed from 5-10 views that were already available in Google Shopping! only available in US & on mobile


ira kemelmacher Reposted

Before you “add to cart,” check out every angle. 📸With 3D shopping, you’ll be able to see 360° spins of more products that you’re searching for on Google, starting this fall with sneakers. 🛍👟 #SearchOn


ira kemelmacher Reposted

Feel pleased to show off our upcoming @CVPR paper, HumanNeRF. Our method turns a Youtube video of moving people into a free-viewpoint video! Page: grail.cs.washington.edu/projects/human… Video: youtu.be/GM-RoZEymmw with Brian Curless, @_pratul_, @jon_barron, @kemelmi More in thread! (1/7)


ira kemelmacher Reposted

We are thrilled to announce Imagen, a text-to-image model with unprecedented photorealism and deep language understanding. Explore imagen.research.google and Imagen! A large rusted ship stuck in a frozen lake. Snowy mountains and beautiful sunset in the background. #imagen

Tweet Image 1

ira kemelmacher Reposted

My team at Google Seattle is hiring researchers & engineers to work on improving and scaling neural rendering for object reconstruction. We're a small, focused team trying to bring the latest advances in 3D reconstruction to products at Google. Please reach out if interested!


ira kemelmacher Reposted

I'm glad to announce that StyleSDF was accepted to CVPR2022!!! This couldn't have happened without the help of my amazing collaborators @XuanLuo14, @shanmy1874, @elishechtman , @jjpark3D & @kemelmi Stay tuned for the code release

StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation abs: arxiv.org/abs/2112.11427 project page: stylesdf.github.io



ira kemelmacher Reposted

Excited to share "A Light Stage on Every Desk". We learn a personalized relighting model by capturing a user watching a YouTube video. Joint work with Brian Curless, @kemelmi, and Steve Seitz from @uwcse @UwRealityLab Project Page: grail.cs.washington.edu/projects/Light… [1/4]


ira kemelmacher Reposted

Really happy to receive Best Student Paper Honorable Mentions at @CVPR 2021! Congrats to two amazing undergrads @peter9863 and @andreyabtsev at @uwcse I am really fortunate to work with and mentor them. Cheers to the whole team :) Congrats to all other award recipients!

Tweet Image 1

ira kemelmacher Reposted

Our work has been accepted as Oral in CVPR 2021. Congrats to @peter9863 and @andreyabtsev for leading this project!

Excited to release v2.0 of our Background Matting project, which is now REAL-TIME & BETTER quality: 60fps at FHD and 30fps at 4K! You can use this with Zoom, check out our demo! 👇 Webpage: grail.cs.washington.edu/projects/backg… Video: youtube.com/watch?v=IYlJJX… More in the thread! [1/6]



ira kemelmacher Reposted

Excited to share our virtual try-on method, VOGUE, from my Google Research internship with @kemelmi! vogue-try-on.github.io We achieve photo-realistic results through interpolation optimization using a pose-conditioned StyleGAN2 network that outputs segmentations & images 1/3


Loading...

Something went wrong.


Something went wrong.