Digests » 153

this week's favorite

Unsupervised 3D neural rendering of Minecraft worlds

We present GANcraft, an unsupervised neural rendering framework for generating photorealistic images of large 3D block worlds such as those created in Minecraft. Our method takes a semantic block world as input, where each block is assigned a label such as dirt, grass, tree, sand, or water. We represent the world as a continuous volumetric function and train our model to render view-consistent photorealistic images from arbitrary viewpoints, in the absence of paired ground truth real images for the block world. In addition to camera pose, GANcraft allows user control over both scene semantics and style.

Scikit-Learn, meet Production

The idea of making an initial ‘Hello, production’ release has had a big influence on how we think about the development of machine learning systems. We’ve mapped ‘Hello, Production’ into the machine learning space.

Image & video background removal using deep learning

Background Removal is a process of separating the main object/image from its background. Deep learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning

Introducing 🤗 Accelerate

Most high-level libraries above PyTorch provide support for distributed training and mixed precision, but the abstraction they introduce require a user to learn a new API if they want to customize the underlying training loop. 🤗 Accelerate was created for PyTorch users who like to have full control over their training loops but are reluctant to write (and maintain) the boilerplate code needed to use distributed training (for multi-GPU on one or several nodes, TPUs, ...) or mixed precision training. Plans forward include support for fairscale, deepseed, AWS SageMaker specific data-parallelism and model parallelism.

NeRF: representing scenes as neural radiance fields for view synthesis

View Synthesis is a tricky problem, especially when only given a sparse set of images as an input. NeRF embeds an entire scene into the weights of a feedforward neural network, trained by backpropagation through a differential volume rendering procedure, and achieves state-of-the-art view synthesis. It includes directional dependence and is able to capture fine structural details, as well as reflection effects and transparency.