daniyar-niantic

FastPhotoStyle

Style transfer, deep learning, feature transform

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

ssd.pytorch

A PyTorch Implementation of Single Shot MultiBox Detector

MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

LoFTR

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

sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

DROID-SLAM

OWOD

(CVPR 2021 Oral) Open World Object Detection

OnePose

Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

GAN_stability

Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"

d2-net

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

awesome-local-global-descriptor

My personal note about local and global descriptor

kapture

kapture is a file format as well as a set of tools for manipulating datasets, and in particular Visual Localization and Structure from Motion data.

COTR

Code release for "COTR: Correspondence Transformer for Matching Across Images"(ICCV 2021)

powerful-benchmarker

A library for ML benchmarking. It's powerful.

stereo-from-mono

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

SynthDet

SynthDet - An end-to-end object detection pipeline using synthetic data

RansacLib

Template-based implementation of RANSAC and its variants in C++

PeopleSansPeople

Unity's privacy-preserving human-centric synthetic data generator

ASLFeat

Implementation of CVPR'20 paper - ASLFeat: Learning Local Features of Accurate Shape and Localization

sfm-disambiguation-colmap

Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures

anonymizer

**ARCHIVED** An anonymizer to obfuscate faces and license plates.

pyceres

Factor graphs with Ceres in Python

TorchIntegral

Integral Neural Networks in PyTorch

FM-Bench

An Evaluation of Feature Matchers for Fundamental Matrix Estimation (BMVC 2019)

depth-from-polarisation

Linear depth estimation from an uncalibrated, monocular polarisation image

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

11785-CMU---FCOS-with-MLFPN