_TFGraphics_

📢📢📢 Happy to introduce that "Kubric: a scalable dataset generator" was accepted at #CVPR2022. arxiv.org/abs/2203.03570 – 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 🧵👇

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! github.com/tensorflow/gra…

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: dellaert.github.io/NeRF/

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 montrealrobotics.ca/diffcvgp/ @MontrealRobots @Mila_Quebec @UofTRobotics (1/3)

Our new paper "𝐔𝐧𝐬𝐮𝐩𝐞𝐫𝐯𝐢𝐬𝐞𝐝 𝐩𝐚𝐫𝐭 𝐫𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐛𝐲 𝐅𝐥𝐨𝐰 𝐂𝐚𝐩𝐬𝐮𝐥𝐞𝐬" is out arxiv.org/abs/2011.13920 TL;DR: are newborns exposed to 14 million (i.e. ImageNet) labeled images? No! They learn by observing motion... in an unsupervised fashion

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

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} ubc-vision.github.io/derf

CvxNet was presented at CVPR 2020, and it is implemented with TensorFlow Graphics! github.com/tensorflow/gra…

The code of Neural Articulated Shape Approximation is now released in our projects page! github.com/tensorflow/gra…

TensorFlow Graphics is an official Google Open Source project. We're excited about our next steps! opensource.google/projects/tenso…

You can now import 3D datasets such as ModelNet and ShapeNet and use them in your pipelines easily! github.com/tensorflow/gra…

We just published our roadmap for the next few months on GitHub. github.com/tensorflow/gra… Any feedback is welcome!

TensorFlow Graphics was released one year ago at Google I/O! You can find our introduction blog post in blog.tensorflow.org/2019/05/introd…

Have you seen our Mesh Segmentation demo? You can train the model from scratch for free in Colab! colab.research.google.com/github/tensorf…

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. youtube.com/watch?v=JuH79E…

This is an excellent resource to learn about 3D Deep Learning with TensorFlow 2. Enjoy! inovex.de/blog/3d-deep-l…

Did you miss the @TensorFlow Developer Summit? Make sure to check it out at youtube.com/playlist?list=…

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 → goo.gle/2xG7ymg

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: summerofcode.withgoogle.com/organizations/…