Niantic Labs

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

simplerecon

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

acezero

[ECCV 2024 - Oral] 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.

manydepth

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

mickey

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

stereo-from-mono

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

ace

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

spz

File format for 3D Gaussian splats. About 10x smaller than the PLY equivalent with virtually no perceptible loss in visual quality. Offered as open source by Niantic Labs. More details at https://scaniverse.com/spz #3dgaussiansplats #gaussiansplatting

venator

A flexible threat detection platform that simplifies rule management and deployment using K8s CronJob and Helm, but can also run standalone or with other job schedulers like Nomad.

diffusionerf

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

map-free-reloc

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

wavelet-monodepth

[CVPR 2021] Monocular depth estimation using wavelets for efficiency

footprints

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

depth-hints

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

doubletake

[ECCV 2024] DoubleTake: Geometry Guided Depth Estimation

marepo

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

nerf-object-removal

[CVPR 2023] Removing Objects From Neural Radiance Fields

implicit-depth

[CVPR 2023] Virtual Occlusions Through Implicit Depth

scoring-without-correspondences

[CVPR 2023] Two-view Geometry Scoring Without Correspondences

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

airplanes

[CVPR 2024] AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings

image-box-overlap

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

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

HandDGP

[ECCV 2024] HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning

metagame-balance

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

nianticlabs.github.io

time-repeatability

[ICRA 2021] Learning to Predict Repeatability of Interest Points

nagatha

Nagatha - Alerts without fatigue