-
Computer Vision Laboratory, Linköping University
- pavlomelnyk.com
Stars
🎓 无需编写任何代码即可轻松创建漂亮的学术网站 Easily create a beautiful academic résumé or educational website using Hugo and GitHub. No code.
A minimal PyTorch implementation of Bundle Adjustment
[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation
Vector Neuron pointcloud networks for classification and segmentation. Separate training setups for VN-DGCNN and VN-PointNet
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
A steerer for D-dimensional keypoint descriptions is a DxD matrix that transforms the descriptions as if they were computed from a rotated image.
Paper list for equivariant neural network
An on-going paper list on new trends in 3D vision with deep learning
An easy-to-use Python library for processing and manipulating 3D point clouds and meshes.
Pytorch implementation of set transformer
BabelCalib: A Universal Approach to Calibrating Central Cameras. In ICCV (2021)
Scalable Data Science, course sets in big data Using Apache Spark over databricks and their mathematical, statistical and computational foundations using SageMath.
Black-box Optimizer based on Bayesian Optimization