Preface renders novel views of faces at ultra-high 4K resolution from very few input images. Stop by the #ICCV2023 Google booth today at 12:30 PM to learn how this approach generalizes to images captured in-the-wild using a mobile camera. Learn more →
@googleai
-
Google Pixel 8 Pro Magic Eraser Generative AI Demo
By
–
Today at 10:30 AM, drop by the #ICCV2023 Google booth to see a demo of the new magic eraser on the Pixel 8 Pro that uses generative AI to enable improved inpainting and better suggestions that properly remove shadows and attached objects. Learn more at:
-
JAX Library Enables Computer Vision on Spherical Surfaces
By
–
Applying computer vision models designed for planar images to data projected on spherical surfaces is challenging. Here we present an open-source library in JAX to solve the challenges of rotation and regular sampling for state-of-the-art performance → https://t.co/wXdIpkmtDy pic.twitter.com/0mC7PdeLW4
— Google AI (@GoogleAI) 4 octobre 2023Applying computer vision models designed for planar images to data projected on spherical surfaces is challenging. Here we present an open-source library in JAX to solve the challenges of rotation and regular sampling for state-of-the-art performance → https://
goo.gle/46z3vD7 -
Open Images Dataset Advances Scene Understanding at ICCV2023
By
–
Open Images contains ~9M images with labels spanning thousands of categories. Visit the #ICCV2023 Google booth today at 3:30 PM to find out how this dataset stimulates progress toward genuine scene understanding. Learn more at https://
g.co/dataset/open-i
mages
… and http://
goo.gle/3FiGPgk -
In-Context Learning for Novel Subject Rendering Without Fine-Tuning
By
–
Drop by the #ICCV2023 Google booth today at 12:30 PM to learn about an in-context learning technique that, given examples of a new subject (e.g., sunglasses, a dog), generates novel renderings of it in different scenes, without the need for fine-tuning.
-
Google Showcases Latest Computer Vision Innovations at ICCV
By
–
At @ICCVConference
? We hope you’ll visit the Google booth to chat with researchers who are actively pursuing the latest innovations in computer vision! Read about our #ICCV2023 involvement and see the booth activity schedule at https://
goo.gle/3PCSnhJ -
Student Wins ICCV Best Paper Award for Tracking Research
By
–
Congratulations to @QianqianWang5 for winning the 2023 Best Student Paper Award at #ICCV2023 for the “Tracking Everything Everywhere All at Once” paper, which she wrote along with Aleksander Holynski, Noah Snavely, Zhengqi Li, and others.
-
Future Research@ Event Topics: Community Input and Suggestions
By
–
What topics would you like to see explored at a future Research@ event? Share your thoughts below
-
Google Research Event Showcases AI Education and LLM Advances
By
–
Another inspiring Research@ event comes to a close in Mexico City! Hosted by Google Research, this event featured lightning talks and interactive demos from researchers covering important topics like Education, Science, Generative AI, and LLMs.
-
Distilling Step-by-Step: Efficient Task-Specific Model Training
By
–
Today on the blog we introduce distilling step-by-step, a new resource-efficient mechanism for training smaller task-specific models that uses much less training data than required by standard fine-tuning or distillation approaches. → https://
goo.gle/450XgHk