Visual Place Recognition ML Frameworks

Methods and systems for identifying and matching locations across images using visual features, descriptors, and retrieval techniques. Includes geo-localization, loop closure detection, and cross-modal localization. Does NOT include general image retrieval, object detection, semantic segmentation, or map construction/rendering.

There are 59 visual place recognition frameworks tracked. 1 score above 50 (established tier). The highest-rated is magicleap/SuperGluePretrainedNetwork at 51/100 with 3,967 stars. 1 of the top 10 are actively maintained.

Get all 59 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=visual-place-recognition&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

# Framework Score Tier
1 magicleap/SuperGluePretrainedNetwork

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

51
Established
2 patrick-llgc/Learning-Deep-Learning

Paper reading notes on Deep Learning and Machine Learning

46
Emerging
3 eric-yyjau/pytorch-superpoint

Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629

44
Emerging
4 changhao-chen/deep-learning-localization-mapping

A collection of deep learning based localization models

44
Emerging
5 lucasb-eyer/pydensecrf

Python wrapper to Philipp Krรคhenbรผhl's dense (fully connected) CRFs with...

44
Emerging
6 zhou13/lcnn

LCNN: End-to-End Wireframe Parsing

42
Emerging
7 aayushbansal/PixelNet

The repository contains source code and models to use PixelNet architecture...

41
Emerging
8 anuragranj/spynet

Spatial Pyramid Network for Optical Flow

41
Emerging
9 aqibsaeed/Place-Recognition-using-Autoencoders-and-NN

Place recognition with WiFi fingerprints using Autoencoders and Neural Networks

41
Emerging
10 bertjiazheng/awesome-scene-understanding

๐Ÿ˜Ž A list of awesome scene understanding papers.

39
Emerging
11 PFCCLab/Open3D

Open3D: A Modern Library for 3D Data Processing

38
Emerging
12 Mrmoore98/VectorMapNet_code

This is the official code base of VectorMapNet (ICML 2023)

38
Emerging
13 Arlo0o/HTCL

[ECCV 2024, IEEE TPAMI] Official PyTorch Implementation of HTCL :...

37
Emerging
14 bertjiazheng/Awesome-CAD

๐Ÿ˜Ž A list of awesome Computer-Aided Design (CAD) papers

37
Emerging
15 Pilhyeon/Learning-Action-Completeness-from-Points

Official Pytorch Implementation of 'Learning Action Completeness from Points...

37
Emerging
16 jac99/MinkLoc3Dv2

MinkLoc3Dv2: Improving Point Cloud Based Place Recognition with...

36
Emerging
17 hli1221/imagefusion_deeplearning

VggML (ICPR 2018, Beijing)

34
Emerging
18 xyzforever/BEVT

PyTorch implementation of BEVT (CVPR 2022) https://arxiv.org/abs/2112.01529

34
Emerging
19 csiro-robotics/Wild-Places

๐Ÿž๏ธ [IEEE ICRA2023] The official repository for paper "Wild-Places: A...

34
Emerging
20 LeonHLJ/RSKP

The official implementation of 'Weakly Supervised Temporal Action...

34
Emerging
21 rayguan97/GANav-offroad

This is the code base for GANav: Group-wise Attention Network for...

34
Emerging
22 tejakattenborn/AngleCAM

A deep learning-based method to infer leaf angle variation from photographs.

33
Emerging
23 csiro-robotics/InCloud

[IROS2022] Official repository of InCloud: Incremental Learning for Point...

31
Emerging
24 lmy98129/VLPD

Official Code of CVPR'23 Paper "VLPD: Context-Aware Pedestrian Detection via...

30
Emerging
25 vvincenttttt/Awesome-3D-Object-Detection

Papers, code and datasets about deep learning for 3D Object Detection.

29
Experimental
26 cyran-kyle/c-3dr

๐Ÿš€ Enhance 3D printing with C-3DR, a tool that simplifies design and...

28
Experimental
27 princeton-computational-imaging/MaskToF

Official code repository for the paper: "Mask-ToF: Learning Microlens Masks...

28
Experimental
28 vlfom/RNCDL

[NeurIPS 2022] The official implementation of "Learning to Discover and...

27
Experimental
29 sar-gupta/weakly-supervised-localization-survey

Survey of various algorithms for weakly supervised object localization using...

27
Experimental
30 engelnico/point-transformer

This is the official repository of the original Point Transformer architecture.

26
Experimental
31 CEA-LIST/tri3d

A unified interface to various 3D driving datasets

26
Experimental
32 Rishit-dagli/3d-transforms

3D Transforms is a library to easily work with 3D data and make 3D...

26
Experimental
33 RenHuan1999/CVPR2023_P-MIL

The official implementation of 'Proposal-based Multiple Instance Learning...

25
Experimental
34 MaxChanger/awesome-point-cloud-scene-flow

A list of point cloud scene flow papers, codes and datasets.

25
Experimental
35 hzwer/Awesome-Optical-Flow

This is a list of awesome paper about optical flow and related work.

25
Experimental
36 amirhossein-razlighi/mlx3D

A library for working with 3D data using mlx

24
Experimental
37 LengSicong/Tell2Design

[ACL2023 Area Chair Award] Official repo for the paper "Tell2Design: A...

23
Experimental
38 TOPO-EPFL/CrossLoc-Benchmark-Datasets

[CVPR'22] CrossLoc benchmark datasets setup and helper scripts.

23
Experimental
39 JackSnowWolf/video-object-segmentation

video object segmentation

22
Experimental
40 Raessan/optical_flow_dinov3

Lightweight head for optical flow using DINOv3 as backbone

22
Experimental
41 arplaboratory/QAA

[ICRA 2026] Official repository for "Query-Based Adaptive Aggregation for...

22
Experimental
42 entvistastudio/metrixel-3d-dataset-tools

Tools for visualizing PyTorch 3D mesh datasets generated from FBX, GLTF, and...

22
Experimental
43 pipixin321/HR-Pro

[AAAI 2024] Official implementation of "Point-supervised Temporal Action...

22
Experimental
44 lambert-x/video-semisup

Learning from Temporal Gradient for Semi-supervised Action Recognition (CVPR 2022)

22
Experimental
45 lmy98129/UMPD

Official Code of ACM MM'24 Paper "Unsupervised Multi-view Pedestrian Detection"

21
Experimental
46 wendashi/awesome-3D-base-models

Similar to the 2D Base Model, 3D Base Model is a bridge between images and 3D data.

21
Experimental
47 line/Skeleton-Temporal-Action-Localization

Official implementation of AAAI 2023 Oral Paper "Frame-Level Label...

20
Experimental
48 Raessan/semantic_segmentation_dinov3

Lightweight head for semantic segmentation using DINOv3 as backbone

19
Experimental
49 gaomingqi/VOS-Review

Datasets and Papers (with codes) discussed in "Deep Learning for Video...

18
Experimental
50 sakshikakde/AutoPano

Panoramic Image stitching using traditional and supervised and unsupervised...

17
Experimental
51 K-bNd/DINOv1_implem

DINOv1 implementation in Pytorch

16
Experimental
52 Mobiwn/vggt_presentation

Interactive Streamlit simulations and presentation materials exploring VGGT...

16
Experimental
53 Amirreza81/Fundamental-3D-Computer-Vision

Implementing some topics in 3D Computer Vision from scratch

15
Experimental
54 UsmanMaqbool/why-so-deep

Why-So-Deep: Towards Boosting Previously Trained Models for Visual Place...

14
Experimental
55 XpiderService/mvggt

๐Ÿ” Capture and segment multiview 3D expressions using our Multimodal Visual...

14
Experimental
56 Simon123123/MSMVF_VVC_TIP2023

Code implementation and dataset of <

14
Experimental
57 Factral/image-stitching-supeglue

image stitching using superglue

13
Experimental
58 barwojcik/dense_direction

A framework for weakly-supervised dense direction estimation of linear...

11
Experimental
59 christofel04/Advanced-Fast-and-Accurate-3D-Object-Detection-using-ResNet-and-Feature-Pyramid-Network

Advanced Fast and Accurate 3D Object Detection using ResNet Architecture and...

10
Experimental