Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (NeurIPS 2022)

[NeurIPS 2023 Track Datasets and Benchmarks] OpenLane-V2: The First Perception and Reasoning Benchmark for Road Driving

Waymo Open Dataset

Let us control diffusion models!

Argoverse 2: Next generation datasets for self-driving perception and forecasting.

Instant neural graphics primitives: lightning fast NeRF and more

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

A procedural Blender pipeline for photorealistic training image generation

Plenoxels: Radiance Fields without Neural Networks

Pose estimation of 3 views based on the trifocal tensor and the fundamental matrix.

Neural Scene Flow Prior (NeurIPS 2021 spotlight)

Official code for "Structured Bird’s-Eye-View Traffic Scene Understanding from Onboard Images" (ICCV 2021)

Audio Visual Floorplan Reconstruction

Cached output for different components of GTSFM

Zillow Indoor Dataset

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

Sampling profiler for Python programs

Open3D: A Modern Library for 3D Data Processing

Object detection on multiple datasets with an automatically learned unified label space.

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

Model interpretability and understanding for PyTorch

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

A technical report on convolution arithmetic in the context of deep learning

MONeT framework for reducing memory consumption of DNN training

Template for GPU accelerated python libraries

Code release for "Rethinking Pseudo-LiDAR Representation (ECCV2020)".

This repository contains implementations and illustrative code to accompany DeepMind publications

Python 3.8+ toolbox for submitting jobs to Slurm