Self-reimplemented version of Long-LRM.

3D Reconstruction for all

3d without friction (Torch, TF, Jax, Numpy)

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Code release for HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling

[NeurIPS2022] Official implementation of PeRFception: Perception using Radiance Fields.

A Blender addon for rendering NeRFs - Under construction, check back soon!

Pen and paper exercises in machine learning

Implementation of "Large Steps in Inverse Rendering of Geometry"

A Synthetic Immersive Large-Volume Plenoptic Dataset

[CVPR 2022] DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting

An open source implementation of CLIP.

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

Public repository of the 3DV 2021 paper "Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds"

[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

Lightning fast C++/CUDA neural network framework

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

The implementation of "In-Place Scene Labelling and Understanding with Implicit Scene Representation" [ICCV 2021].

This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

A library for solving the satellite structure from motion problem

VRT: A Video Restoration Transformer (official repository)

Mesh parameterization / UV unwrapping library

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

FFCV: Fast Forward Computer Vision (and other ML workloads!)

STL to ASCII Generator

Instant neural graphics primitives: lightning fast NeRF and more