GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • nianticlabs
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles

This view

  • Original page
  • New address

GeezerVison is showing github.com — Niantic Labs

Popular repositories Loading

  1. monodepth2 monodepth2 Public

    [ICCV 2019] Monocular depth estimation from a single image

    Jupyter Notebook 4.5k 986

  2. simplerecon simplerecon Public

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

    Python 1.4k 130

  3. spz spz Public

    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://s…

    C++ 943 116

  4. acezero acezero Public

    [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.

    Python 811 56

  5. manydepth manydepth Public

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

    Python 665 83

  6. mickey mickey Public

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

    Python 592 39

Repositories

Loading
Type
Language
Sort
Showing 10 of 33 repositories
  • spz Public

    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

    nianticlabs/spz's past year of commit activity
    C++ 943 MIT 116 29 9 Updated Nov 10, 2026
  • monodepth2 Public

    [ICCV 2019] Monocular depth estimation from a single image

    nianticlabs/monodepth2's past year of commit activity
    Jupyter Notebook 4,513 986 28 4 Updated Nov 2, 2026
  • map-free-reloc Public

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

    nianticlabs/map-free-reloc's past year of commit activity
    Python 319 20 1 0 Updated Oct 21, 2026
  • mvsanywhere Public
    nianticlabs/mvsanywhere's past year of commit activity
    Python 347 19 11 0 Updated Jun 30, 2026
  • acezero Public

    [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.

    nianticlabs/acezero's past year of commit activity
    Python 811 56 1 0 Updated Nov 10, 2025
  • placeit3d Public

    [ICCV 2025] PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes

    Uh oh!

    There was an error while loading. Please reload this page.

    nianticlabs/placeit3d's past year of commit activity
    Python 69 5 4 0 Updated Oct 3, 2025
  • nianticlabs.github.io Public
    nianticlabs/nianticlabs.github.io's past year of commit activity
    HTML 5 2 0 0 Updated Oct 3, 2025
  • morpheus Public
    nianticlabs/morpheus's past year of commit activity
    Python 32 3 1 0 Updated Jul 3, 2025
  • implicit-depth Public

    [CVPR 2023] Virtual Occlusions Through Implicit Depth

    nianticlabs/implicit-depth's past year of commit activity
    Python 88 5 1 0 Updated May 9, 2025
  • doubletake Public

    [ECCV 2024] DoubleTake: Geometry Guided Depth Estimation

    nianticlabs/doubletake's past year of commit activity
    Python 191 13 2 1 Updated May 9, 2025
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Python Jupyter Notebook Go C++ HTML

Most used topics

computer-vision depth-estimation pytorch deep-learning pose-estimation
You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.