Name: Vincent Sitzmann
Type: User
Company: Massachusetts Institute of Technology
Bio: Assistant Professor @mit EECS. I'm researching self-supervised learning for vision - how can we build an AI that learns to perceive the world the way we do?
Twitter: vincesitzmann
Location: Cambridge, Massachusetts
Blog: https://vsitzmann.github.io/
Vincent Sitzmann's Projects
A curated list of resources on implicit neural representations.
A tiny example application of pytorch_prototyping, with an example training script.
Scripts to setup remote instances with starter environment.
Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"
LSD-SLAM
Official implementation of "MetaSDF: Meta-learning Signed Distance Functions"
A collection of the application documents I used to apply to universities in the US.
Easy-to-use glTF 2.0-compliant OpenGL renderer for visualization of 3D scenes.
Custom pytorch modules with sane default parameters useful for model prototyping. (U-Net, upsampling, downsampling...)
Official Pytorch implementation of Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
A clean, compact renderer for spherical images of shapenet objects in blender <2.8.
tensorflow implementation of show attend and tell
Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
Tensorflow implementation of the Long-Short Term Memory Network with Deep Attention Fusion for the SNLI dataset.
Computation using data flow graphs for scalable machine learning
DeepLab-ResNet rebuilt in TensorFlow
An Implementation of Fully Convolutional Networks in Tensorflow.