Sofien Bouaziz

The 6th #CV4ARVR workshop, conducted in conjunction with @CVPR 2022, is now accepting submissions. Please submit a 2-3 page extended abstract by 4/9! xr.cornell.edu/workshop/2022/…

We are looking for talented Research Interns to join the FRL XR People team and work on exciting R&D problems. Our team is focused on developing novel human understanding technologies on AR and VR devices. To apply follow this link facebookcareers.com/jobs/689940858…

There is an updated link facebook.com/careers/v2/job…

We are looking for talented Research Interns to join the FRL XR People team and work on exciting R&D problems. Our team is focused on developing novel human understanding technologies for AR/VR. To apply follow this link --> facebook.com/careers/v2/job…

and reconstruction (e.g. NeRF), image synthesis (e.g. GAN), segmentation, differentiable rendering, novel text input techniques, novel sensors / sensor fusion (e.g. EMG, accelerometer, ...) and efficient ML techniques to run these methods on AR/VR devices.

We would like to support students who are working on advancing the state-of-the-art in human understanding for AR/VR. Topics of interest include, but are not limited to, tracking and modelling humans and objects, action and gesture recognition, non-rigid fusion

Apply to the Facebook Fellowship Program, we are going to support PhD students in the area of AR/VR Human Understanding! research.fb.com/fellowship/

The deadline is approaching! Submit your best work to the 5th workshop on Computer Vision for AR/VR, in conjunction with ICCV 2021. xr.cornell.edu/workshop/2021/…

Call for papers for the 5th workshop on Computer Vision for AR/VR, in conjunction with ICCV 2021. Deadline July 30th 2021. Submit your best work and spread the word!!! xr.cornell.edu/workshop/2021/…

Introducing HyperNeRF! By lifting NeRF into higher dimensions, we fix a big limitation of Nerfies: topological changes. HyperNeRF can handle topological variations such as facial expressions that Nerfies can't. Website: hypernerf.github.io arXiv: arxiv.org/abs/2106.13228 (1/N)

Today we're releasing the code for Nerfies! We've also included a Colab demo so that you can try out a basic version of our method right in your browser. Project Page: nerfies.github.io Github: github.com/google/nerfies [1/n] 🧵👇

Happy to see some of our work featured in the Google research 2020 highlights: ai.googleblog.com/2021/01/google…

If you were wondering how one can photorealistically reconstruct a non-rigidly deforming scene captured casually from a mobile phone, check out our work on deformable NeRF and how we used it to take selfies.

State of the art work on depth sensing from Vladimir and the team. Fast, accurate and able to leverage small training sets. The approach ranks 1st-3rd on all the ETH3D metrics and also on KITTI 12/15 among the sub 100ms methods. arxiv.org/abs/2007.12140

Experience Augmented Reality like never before! With your smartphone! #depth #depthfrommotion #augmentedreality #smartphoneAR #AR 9to5google.com/2020/06/25/and…

Depth sensing without a depth sensor, on hundreds of millions Android phones. The ARCore Depth API rolls out today → goo.gle/ARCore-Depth-A…

Join us at @cvpr2020! This year we organized a tutorial on how to leverage performance capture for perception tasks. We also talk about neural rendering and its applications! More info at seanfanello.it/2020/06/06/cvp… #deeplearning #neuralrendering #volumetriccapture #computergraphics

Check out our tutorial on Disentangled 3D Representations for Relightable Performance Capture of Humans ! #CVPR2020 augmentedperception.github.io/cvpr2020/ From high quality depth sensing to neural rendering!

Join us tomorrow for the CVPR20 AR/VR workshop via Zoom! Eight exceptional speakers will discuss a variety of topics in new immersive technologies with AR/VR. mixedreality.cs.cornell.edu/workshop/2020/…

If you are at #NeurIPS2019 , don't miss our paper on sparse multi-view (1 or more) object reconstruction. **Wed Dec 11th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #96** Joint work with: @davrempe @JPCValentin @_sofien_ Leo Guibas. @NeurIPSConf