soskek

bookcorpus

Crawl BookCorpus

turnover_dropout

twitter_conversation_crawler

For crawling conversational tweet threads; e.g. datasets for chatbots.

DALL-E

PyTorch package for the discrete VAE used for DALL·E.

data

DROID-SLAM

glide-text2im

GLIDE: a diffusion-based text-conditional image synthesis model

Hierarchical-Localization

Visual localization made easy with hloc

hypernerf

Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".

hyperreel

Code release for HyperReel High-Fidelity 3D Video with Ray-Conditioned Sampling

inside_mesh

A teensy repo that allows me to use a function from the awesome occupancy_networks codebase.

K-Planes

kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

lama

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

lama-cleaner

Image inpainting tool powered by SOTA AI Model

lang-seg

Language-Driven Semantic Segmentation

nerf

Neural Radiance Fields in PyTorch

nerfstudio

A collaboration friendly studio for NeRFs

object_nerf

Code for "Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering", ICCV 2021

python-plyfile

NumPy-based text/binary PLY file reader/writer for Python

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

SCNeRF

[ICCV21] Self-Calibrating Neural Radiance Fields

soskek.github.io

StreamRF

Official implementation of our NeurIPS paper "Streaming Radiance Fields for 3D Video Synthesis"

svox2

Plenoxels: Radiance Fields without Neural Networks, Code release WIP

tiny-cuda-nn

Lightning fast C++/CUDA neural network framework

torch-ngp

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

ublacklist-stackoverflow-translation

Stack Overflow の機械翻訳サイトの除外用フィルタ

website

XQA

Dataset and baseline for ACL 2019 paper "XQA: A Cross-lingual Open-domain Question Answering Dataset"