-
Nanyang Technological University
- Singapore
- https://scholar.google.com/citations?user=-p7HvCMAAAAJ&hl=zh-CN
Starred repositories
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
PyTorch code and models for the DINOv2 self-supervised learning method.
Minimal solvers for calibrated camera pose estimation
Image registration based on the Fourier-Mellin transform
A multi-modal, photo-realistic dataset for online end-to-end scene change detection and more (accepted to IROS2021).
Releasing a novel dataset taken in a Clearpath Robotics warehouse.
iSLAM: Imperative SLAM (RA-L 2024) is a novel Visual-Inertial SLAM using Self-supervised Learning
[ICRA 2024] Outram: One-shot Global Localization via Triangulated Scene Graph and Global Outlier Pruning
A curated list of awesome visual localization research works.
Header-only C++/python library for fast approximate nearest neighbors
[RAL 2024] D2S: Representing sparse descriptors and 3D coordinates for camera relocalization
[CVPR 2023 - Highlight] Accelerated Coordinate Encoding (ACE): Learning to Relocalize in Minutes using RGB and Poses
The official PyTorch implementation of the paper: *Xili Dai, Haigang Gong, Shuai Wu, Xiaojun Yuan, Yi Ma. "Fully Convolutional Line Parsing." *.
Training library for local feature detection and matching
A research protocol for deep graph matching.
Drawing Bayesian networks, graphical models, tensors, technical frameworks, and illustrations in LaTeX.
republish livox raw message to standard pointcloud2
2-Line Exhaustive Searching for Real-Time Vanishing Point Estimation in Manhattan World
Holistically-Attracted Wireframe Parsing [TPAMI'23] & [CVPR' 20]
Implementation of Monocular Direct Sparse Localization in a Prior 3D Surfel Map (DSL)
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"
Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences
Official implementation of "Decentralization and Acceleration Enables Large-Scale Bundle Adjustment"
[CVPR 2023] "Revisiting Rotation Averaging: Uncertainties and Robust Losses" by Ganlin Zhang, Viktor Larsson and Daniel Barath
A toolbox for mapping and localization with line features.