Last week, I was lucky to go to Vancouver for #CVPR2023 and unexpectedly found Digital Orca, a sculpture famous for every person who has worked with voxelized meshes at least once... 😄
What a nice trip...

One thing about being in Vancouver for #CVPR2023 is that Canada lives up to the reputation of having terrible internet

Have not had a solid internet connection anywhere I’ve been— wtf #Canada

A dance floor that’s 90% male doesn’t really work #cvpr2023

RT @danielajisafe@twitter.com

Dr @mennatullahSiam@twitter.com, co-founder of the Ro'ya-CV4Africa community touched on the wonderful initiatives and community-driven projects led by the group @RoyaCV4Africa@twitter.com @CVPR@twitter.com #CVPR2023

🐦🔗: https://twitter.com/danielajisafe/status/1671584266260553753

RT @GoogleAI@twitter.com

Introducing MAGVIT, a single transformer designed to address ten video generation tasks, including future image animation, video editing and video outpainting. Stop by the #CVPR2023 Google booth at 10am today to see it in action! More details at: https://magvit.cs.cmu.edu/

🐦🔗: https://twitter.com/GoogleAI/status/1671548905094348814

Rodney Brooks #CVPR2023 keynote about his PhD in the 70s: “In four years I processed three images.”

So far have been very impressed by the restaurants and cafes in #vancouver #cvpr2023

💡 #CVPR2023 (Computer Vision and Pattern Recognition) is on

Sun, Jun 18 through Thu, Jun 22 at the Vancouver Convention Center

Web Site
https://cvpr2023.thecvf.com

Each year, there are a tremendous amount of research papers presented at this conference

#RSIPVision publishes a magazine covering the news revealed each day at the show. They ask you to sign up for a newsletter to receive these, but they also provide a link to each issue on their Twitter feed the following day https://twitter.com/RSIPvision

On my way to #cvpr2023. Could not be more excited!

Poster presentation (PM session) at #CVPRW2023 "CV4Animals" at #CVPR2023 in #Vancouver

Poster presentation (AM session) at #CVPRW2023 "CV4Animals" at #CVPR2023 in #Vancouver

Poster presentation (AM session) at #CVPRW2023 "CV4Animals" at #CVPR2023 in #Vancouver

made it to vancouver for #cvpr2023, really excited to host our 5th annual VizWiz Workshop, with three outstanding keynote speakers -- representing users, researchers, and industry --

more here:
https://vizwiz.org/workshops/2023-workshop/

🚨Crowded scenes are notoriously difficult for #ComputerVision models.
In our new work lead by PhD students Mu Zhou & Lucas Stoffl we developed a novel approach called BUCTD that is state-of-the-art on crowded 🐒🐠&🕺human pose estimation benchmarks!🔥
Http://arxiv.org/abs/2306.07879
#CVPR2023 workshop

Happy to announce that our paper "Inferring the Past: A Combined CNN-LSTM Deep Learning Framework To Fuse Satellites for Historical Inundation Mapping" was accepted at CVPR workshop Earthvision!

https://openaccess.thecvf.com/content/CVPR2023W/EarthVision/html/Giezendanner_Inferring_the_Past_A_Combined_CNN-LSTM_Deep_Learning_Framework_To_CVPRW_2023_paper.html

#earthvision #CVPR2023

We released our Neural Parametric Head Models (NPHM) dataset from our #CVPR2023 paper!

It includes over 5600 high-fidelity 3D scans of human heads from 272 subjects - all publicly available!

Check it out!
https://simongiebenhain.github.io/NPHM/

We've also released the NPHM code: https://github.com/SimonGiebenhain/NPHM

We provide several examples and a small demo how to use our dataset. It's now super easy to build your own parametric face/head model!

Great work by Simon, Tobias, Markos Martin Lourdes!

[conf.s, social media bans] A large group moved to repeal the social media ban at #CVPR2023 -- motion 3. Vote appropriately if you're attending CVPR this year.

(I am pro repeal.)
#publishing #socialMediaBan

https://www.wjscheirer.com/misc/pamitc/pamitc_newsletter_june_2023.pdf

D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers

Jianfeng He, Yuan Gao, Tianzhu Zhang, Zhe Zhang, Feng Wu

tl;dr: no idea how that works, hierarchical attention something. No eval on #IMC

https://openaccess.thecvf.com/content/CVPR2023/papers/He_D2Former_Jointly_Learning_Hierarchical_Detectors_and_Contextual_Descriptors_via_Agent-Based_CVPR_2023_paper.pdf
#CVPR2023
#computervision #deeplearning
#dmytrotweetsaboutDL

SFD2: Semantic-guided Feature Detection and Description

Fei Xue, Ignas Budvytis, Roberto Cipolla

tl;dr: more principled approach to use segmentation for image matching, than class-name filtering.

https://arxiv.org/abs/2304.14845.pdf

#computervision #deeplearning
#dmytrotweetsaboutDL
#CVPR2023

Check out NPHM!

One of the best parts of writing a paper is the collaboration with great talents. At Synthesia we are working with TUM+UCL and our first publication will be presented at #CVPR2023 🎉 Special thanks to the first author Simon (https://simongiebenhain.github.io) for the fantastic execution.

https://sigmoid.social/@Niessner/110215703459747471