_TFGraphics_

[Andrea Tagliasacchi 🇨🇦→✈️→🇺🇲 (@CVPR) @taiyasaki]

📢📢📢 Happy to introduce that "Kubric: a scalable dataset generator" was accepted at #CVPR2022.
https://t.co/FRFlZHglP7

– Do you work on video and/or 3D vision from images?
– Having a hard time applying the "scientific method" to your research?

Look no further 🧵👇

[_TFGraphics_ @_TFGraphics_]

Full implementation of Neural Radiance Fields now in TF-Graphics, including ray sampling with various strategies (including coarse-to-fine), volumetric rendering, and so on!

https://t.co/7U6qWC1K4a

[Frank Dellaert @fdellaert]

2020 was the year in which *neural volume rendering* exploded onto the scene, triggered by the impressive NeRF paper by Mildenhall et al. I wrote a post as a way of getting up to speed in a fascinating and very young field and share my journey with you: https://t.co/rGUByLBlnl

[Krishna Murthy @ CVPR @_krishna_murthy]

Join us this Friday at the Neurips workshop on Differentiable computer vision, geometry, and physics! Exciting speaker lineup!! Our schedule and accepted papers are up on our webpage https://t.co/HFYHdnYqDf @MontrealRobots @Mila_Quebec @UofTRobotics (1/3)

[Andrea Tagliasacchi 🇨🇦→✈️→🇺🇲 (@CVPR) @taiyasaki]

Our new paper "𝐔𝐧𝐬𝐮𝐩𝐞𝐫𝐯𝐢𝐬𝐞𝐝 𝐩𝐚𝐫𝐭 𝐫𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐛𝐲 𝐅𝐥𝐨𝐰 𝐂𝐚𝐩𝐬𝐮𝐥𝐞𝐬" is out https://t.co/0t4XH4FH8H

TL;DR: are newborns exposed to 14 million (i.e. ImageNet) labeled images? No! They learn by observing motion... in an unsupervised fashion

[Keunhong Park @KeunhongP]

We present nerfies! We use selfie videos to create 3d free-viewpoint portrait visualizations of yourself using Deformable NeRFs! More details at https://t.co/wyBh6Gw6HW and below (1/8)

[Andrea Tagliasacchi 🇨🇦→✈️→🇺🇲 (@CVPR) @taiyasaki]

Rebain et al. "𝐃𝐞𝐜𝐨𝐦𝐩𝐨𝐬𝐞𝐝 𝐑𝐚𝐝𝐢𝐚𝐧𝐜𝐞 𝐅𝐢𝐞𝐥𝐝𝐬 (𝐃𝐞𝐑𝐅)"

That is, the render time of NeRFs can be improved (by +𝟑𝟎𝟎%!) by decomposing the scene representation into many lower-capacity networks.

Collaboration {UBC, Google, SFU}
https://t.co/5FAVAmTKgY

[_TFGraphics_ @_TFGraphics_]

CvxNet was presented at CVPR 2020, and it is implemented with TensorFlow Graphics!
https://t.co/eQzO9tSc8x

[_TFGraphics_ @_TFGraphics_]

The code of Neural Articulated Shape Approximation is now released in our projects page!

https://t.co/iZTu8ha8Jj

[_TFGraphics_ @_TFGraphics_]

CvxNet was presented at CVPR 2020, and it is implemented with TensorFlow Graphics!
https://t.co/eQzO9tSc8x

[_TFGraphics_ @_TFGraphics_]

TensorFlow Graphics is an official Google Open Source project. We're excited about our next steps! https://t.co/h8XBBfSGd9

[_TFGraphics_ @_TFGraphics_]

You can now import 3D datasets such as ModelNet and ShapeNet and use them in your pipelines easily! https://t.co/kQG8zGABRb

[_TFGraphics_ @_TFGraphics_]

We just published our roadmap for the next few months on GitHub. https://t.co/18GlvhS23H Any feedback is welcome!

[_TFGraphics_ @_TFGraphics_]

TensorFlow Graphics was released one year ago at Google I/O! You can find our introduction blog post in
https://t.co/m6kyjMRUMF

[_TFGraphics_ @_TFGraphics_]

Have you seen our Mesh Segmentation demo?

You can train the model from scratch for free in Colab!

https://t.co/8LVgF2G0JK

[_TFGraphics_ @_TFGraphics_]

Check out this great video of Neural Radiance Fields (NeRF)

The idea is to represent a scene using a deep network from a set of images with known camera poses.

https://t.co/WoUcaLCuqM

[_TFGraphics_ @_TFGraphics_]

This is an excellent resource to learn about 3D Deep Learning with TensorFlow 2. Enjoy!
https://t.co/86Hun6bVHb

[_TFGraphics_ @_TFGraphics_]

Did you miss the @TensorFlow Developer Summit? Make sure to check it out at https://t.co/ocJjVak8rC

[TensorFlow @TensorFlow]

We are excited to update the Model Garden for TensorFlow 2 users. Check out new code examples for state-of-the-art models and reusable modeling libraries.

🌷 Read the blog → https://t.co/2uwnYDk7hH

[_TFGraphics_ @_TFGraphics_]

Google Summer of Code is an excellent opportunity to contribute to open source, get exposed to cutting edge research and learn! We have some projects posted in: https://t.co/VzrDICb9eR