335 Open source projects that are alternatives of or similar to PCLoc

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

Visual localization made easy with hloc

Provide mapping and localization pipelines based on kapture format

A general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points or line) map. 3)Fusion framework with IMU, wheel odom and GPS sensors.

[ICCV2021] Learning to Track Objects from Unlabeled Videos

Code for "SRN: Stacked Regression Network for Real-time 3D Hand Pose Estimation" BMVC 2019

kPAM: Generalizable Robotic Manipulation

2020 DIGIX GLOBAL AI CHALLENGE - Digital Device Image Retrieval - Top2 WEARE队

A human perception library

The authors' implementation of the "Neural Head Reenactment with Latent Pose Descriptors" (CVPR 2020) paper.

The relocalization task aims to estimate the 6-DoF pose of a novel (unseen) frame in the coordinate system given by the prior model of the world.

Self-Supervised Depth Estimation on Monocular Sequences

Posture recognition based on common camera

🌅The code of post "Image retrieval using MatconvNet and pre-trained imageNet"

A real-time GNN-based method. Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective

图像配准算法。包括 SIFT、ORB、SURF、AKAZE、BRIEF、matchTemplate

Bottom-up whole-body pose estimation method in constant time.

Image retrieval program made in Tensorflow supporting VGG16, VGG19, InceptionV3 and InceptionV4 pretrained networks and own trained Convolutional autoencoder.

KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation (CVPR 2021)

[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation

[ICLR2022] official implementation of UniFormer

[ICCV 2021] InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring

[ICCV21] Code for "RetrievalFuse: Neural 3D Scene Reconstruction with a Database"

Official repository for "GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition" (ICIP'21)

Search photos on Unsplash based on OpenAI's CLIP model, support search with joint image+text queries and attention visualization.

Light-weight Single Person Pose Estimator

Fast and scalable search of whole-slide images via self-supervised deep learning - Nature Biomedical Engineering

No description or website provided.

🚀 SLAM for autonomous planetary rovers with global localization

This paper is accepted by ICCV 2021.

3D Human Pose Visualizer for Python

Generalized Product Quantization Network For Semi-supervised Image Retrieval - CVPR 2020

[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".

Parametric Contrastive Learning (ICCV2021)

Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021

3d Human Pose Estimation from 2d Keypoints

This repository contains the code of AirPose, our multi-view fusion network for Human Pose and Shape Estimation method

Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)

DREAM: Deep Robot-to-Camera Extrinsics for Articulated Manipulators (ICRA 2020)

Code for "Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation"

An indoor positioning system (IPS) is a system to locate objects or people inside a building using radio waves, magnetic fields, acoustic signals, or other sensory information.

Autonomous ground exploration mobile robot which has 3-DOF manipulator with Intel Realsense D435i mounted on a Tracked skid-steer drive mobile robot. The robot is capable of mapping spaces, exploration through RRT, SLAM and 3D pose estimation of objects around it. This is an custom robot with self built URDF model.The Robot uses ROS's navigation…

Image retrieval learning record

Official PyTorch Implementation of Embedding Transfer with Label Relaxation for Improved Metric Learning, CVPR 2021

Multi-Stage Pose Network

live, low-latency markerless multi-camera 3D animal tracking system

Pytorch version reinplement code of PyraNet , for paper : Learning Feature Pyramids for Human Pose Estimation

Official implementation of deep matching prior

Variants of Vision Transformer and its downstream tasks

The collection of pre-trained, state-of-the-art AI models for ailia SDK

Fast Image Retrieval (FIRe) is an open source project to promote image retrieval research. It implements most of the major binary hashing methods to date, together with different popular backbone networks and public datasets.

Official Code: A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking

Seamless Augmented Reality module for QML using UchiyaMarkers

CVPR 2019: Ranked List Loss for Deep Metric Learning, with extension for TPAMI submission

[ICCV 2021] TRAR: Routing the Attention Spans in Transformers for Visual Question Answering -- Official Implementation

Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)

Content Based Image Retrieval Techniques (e.g. knn, svm using MatLab GUI)

GUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.

Visual Similarity research at Fynd. Contains code to reproduce 2 of our research papers.