Explore @nianticlabs Open Source projects

Niantic Labs (@nianticlabs)

nianticlabs

Stars
8,751
Global Org. Rank 2,656 (Top 0.9 %)
Registered almost 9 years ago
Most used languages

Python
71.4 %

Jupyter Notebook
19.0 %

JavaScript
4.8 %

HTML
4.8 %
Location 🇺🇸 United States
Country Total Rank 1,379
Country Ranking

Jupyter Notebook
64

Python
391

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

Jupyter Notebook

simplerecon

[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions

manydepth

[CVPR 2021] Self-supervised depth estimation from short sequences

stereo-from-mono

[ECCV 2020] Learning stereo from single images using monocular depth estimation networks

mickey

[CVPR 2024 - Oral] Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences

ace

[CVPR 2023 - Highlight] Accelerated Coordinate Encoding (ACE): Learning to Relocalize in Minutes using RGB and Poses

diffusionerf

[CVPR 2023] DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models

wavelet-monodepth

[CVPR 2021] Monocular depth estimation using wavelets for efficiency

Jupyter Notebook

footprints

[CVPR 2020] Estimation of the visible and hidden traversable space from a single color image

map-free-reloc

[ECCV 2022] Map-free Visual Relocalization: Metric Pose Relative to a Single Image

depth-hints

[ICCV 2019] Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs

Jupyter Notebook

acezero

ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.

nerf-object-removal

[CVPR 2023] Removing Objects From Neural Radiance Fields

marepo

[CVPR 2024 Highlight] Map-Relative Pose Regression for Visual Re-Localization

scoring-without-correspondences

[CVPR 2023] Two-view Geometry Scoring Without Correspondences

implicit-depth

[CVPR 2023] Virtual Occlusions Through Implicit Depth

rectified-features

[ECCV 2020] Single image depth prediction allows us to rectify planar surfaces in images and extract view-invariant local features for better feature matching

image-box-overlap

[ECCV 2020] Training neural networks to predict visual overlap of images, through interpretable non-metric box embeddings

Jupyter Notebook

panoptic-forecasting

[CVPR 2021] Forecasting the panoptic segmentation of future video frames

relpose-gnn

[3DV21] Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision, M. Türkoǧlu et al.

modron

Modron - Cloud security compliance

time-repeatability

[ICRA 2020] Learning to Predict Repeatability of Interest Points

nianticlabs.github.io

metagame-balance

[AAMAS 2023] Bilevel Entropy based Mechanism Design for Balancing Meta in Video Games