daikiyamanaka

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

nerfstudio

A collaboration friendly studio for NeRFs

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

dust3r

DUSt3R: Geometric 3D Vision Made Easy

LightGlue

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

UnityGaussianSplatting

Toy Gaussian Splatting visualization in Unity

Anything-3D

Segment-Anything + 3D. Let's lift anything to 3D.

f2-nerf

Fast neural radiance field training with free camera trajectories

glue-factory

Training library for local feature detection and matching

practical-mlops-book

[Book-2021] Practical MLOps O'Reilly Book

openscene

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

Octree-GS

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

OrienterNet

Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"

dynablox

Real-time detection of diverse dynamic objects in complex environments.

mickey

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

wavemap

Fast, efficient and accurate multi-resolution, multi-sensor 3D occupancy mapping

DKM

[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation

map-free-reloc

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

metal-spatial-rendering

A minimal example of rendering an immersive spatial experience with Metal, ARKit, and visionOS Compositing Services

VisFusion

[CVPR 2023] Code for "VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos"

mujoco-python-viewer

Simple renderer for use with MuJoCo (>=2.1.2) Python Bindings.

snap

SNAP: Self-supervised Neural Maps for Visual Positioning and Semantic Understanding (NeurIPS 2023)

Symphonies

[CVPR 2024] Symphonies (Scene-from-Insts): Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

CCCoreLib

C++ library which provides data structures & algorithms for working with 3D point cloud data

RH-Map

RH-Map: Online dynamic objects removal [RA-L 23]

pyTheiaSfM

An open source Python library for multiview geometry and structure from motion

golf_ball