Dmytro Mishkin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Dmytro Mishkin has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Jiri Matas
Center for Machine Perception, Czech Technical University, Prague, Czechia
9 shared publications Jiri Matas
7 shared publications- Filip Radenovic
Meta AI
3 shared publications Michal Perdoch
3 shared publications- Anastasiia Mishchuk
Center for Machine Perception Visual Computing Group Computer Vision Lab University École Polytechnique Fédérale de Lausanne Czech Technical University in Prague
2 shared publications - Eduard Trulls
Google research
2 shared publications
Latest Publications
- 30 September 2024
- Published by Springer Nature
- p. 421-441
StereoGlue: Robust Estimation with Single-Point Solvers
- 30 September 2024
- Published by Springer Nature
- p. 421-441
StereoGlue: Robust Estimation with Single-Point Solvers
- 18 April 2022
- Published by Elsevier in Pattern Recognition Letters
- Vol. 158, 141-147
HarrisZ+: Harris corner selection for next-gen image matching pipelines
- 18 April 2022
- Published by Elsevier in Pattern Recognition Letters
- Vol. 158, 141-147
HarrisZ+: Harris corner selection for next-gen image matching pipelines
- Open Access
Image Matching across Wide Baselines: From Paper to Practice
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the perceived state of the art. Besides establishing the actual state of the art, the conducted experiments reveal unexpected properties of Structure from Motion (SfM) pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online https://github.com/vcg-uvic/image-matching-benchmark, providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both alongside and against top-performing methods. This work provides a basis for the Image Matching Challenge https://vision.uvic.ca/image-matching-challenge.
Open AccessImage Matching across Wide Baselines: From Paper to Practice
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the perceived state of the art. Besides establishing the actual state of the art, the conducted experiments reveal unexpected properties of Structure from Motion (SfM) pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online https://github.com/vcg-uvic/image-matching-benchmark, providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both alongside and against top-performing methods. This work provides a basis for the Image Matching Challenge https://vision.uvic.ca/image-matching-challenge.
- Open Access
Leveraging Outdoor Webcams for Local Descriptor Learning
We present AMOS Patches, a large set of image cut-outs, intended primarily for the robustification of trainable local feature descriptors to illumination and appearance changes. Images contributing to AMOS Patches originate from the AMOS dataset of recordings from a large set of outdoor webcams. The semiautomatic method used to generate AMOS Patches is described. It includes camera selection, viewpoint clustering and patch selection. For training, we provide both the registered full source images as well as the patches. A new descriptor, trained on the AMOS Patches and 6Brown datasets, is introduced. It achieves state-of-the-art in matching under illumination changes on standard benchmarks.
Open AccessLeveraging Outdoor Webcams for Local Descriptor Learning
We present AMOS Patches, a large set of image cut-outs, intended primarily for the robustification of trainable local feature descriptors to illumination and appearance changes. Images contributing to AMOS Patches originate from the AMOS dataset of recordings from a large set of outdoor webcams. The semiautomatic method used to generate AMOS Patches is described. It includes camera selection, viewpoint clustering and patch selection. For training, we provide both the registered full source images as well as the patches. A new descriptor, trained on the AMOS Patches and 6Brown datasets, is introduced. It achieves state-of-the-art in matching under illumination changes on standard benchmarks.
- Top Cited Papers
- 7 October 2020
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (2) , 517-547
Image Matching Across Wide Baselines: From Paper to Practice
- 7 October 2020
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (2) , 517-547
Top Cited PapersImage Matching Across Wide Baselines: From Paper to Practice
- Open Access
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations. Examples of classical vision problems implemented using our framework are provided including a benchmark comparing to existing vision libraries.
Open AccessKornia: an Open Source Differentiable Computer Vision Library for PyTorch
This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations. Examples of classical vision problems implemented using our framework are provided including a benchmark comparing to existing vision libraries.
- Open Access
Benchmarking Classic and Learned Navigation in Complex 3D Environments
Navigation research is attracting renewed interest with the advent of learning-based methods. However, this new line of work is largely disconnected from well-established classic navigation approaches. In this paper, we take a step towards coordinating these two directions of research. We set up classic and learning-based navigation systems in common simulated environments and thoroughly evaluate them in indoor spaces of varying complexity, with access to different sensory modalities. Additionally, we measure human performance in the same environments. We find that a classic pipeline, when properly tuned, can perform very well in complex cluttered environments. On the other hand, learned systems can operate more robustly with a limited sensor suite. Overall, both approaches are still far from human-level performance.
Open AccessBenchmarking Classic and Learned Navigation in Complex 3D Environments
Navigation research is attracting renewed interest with the advent of learning-based methods. However, this new line of work is largely disconnected from well-established classic navigation approaches. In this paper, we take a step towards coordinating these two directions of research. We set up classic and learning-based navigation systems in common simulated environments and thoroughly evaluate them in indoor spaces of varying complexity, with access to different sensory modalities. Additionally, we measure human performance in the same environments. We find that a classic pipeline, when properly tuned, can perform very well in complex cluttered environments. On the other hand, learned systems can operate more robustly with a limited sensor suite. Overall, both approaches are still far from human-level performance.
- 5 October 2018
- Published by Springer Nature
- p. 287-304
Repeatability Is Not Enough: Learning Affine Regions via Discriminability
- 5 October 2018
- Published by Springer Nature
- p. 287-304
Repeatability Is Not Enough: Learning Affine Regions via Discriminability
- Open Access
Repeatability Is Not Enough: Learning Affine Regions via Discriminability
A method for learning local affine-covariant regions is presented. We show that maximizing geometric repeatability does not lead to local regions, a.k.a features,that are reliably matched and this necessitates descriptor-based learning. We explore factors that influence such learning and registration: the loss function, descriptor type, geometric parametrization and the trade-off between matchability and geometric accuracy and propose a novel hard negative-constant loss function for learning of affine regions. The affine shape estimator -- AffNet -- trained with the hard negative-constant loss outperforms the state-of-the-art in bag-of-words image retrieval and wide baseline stereo. The proposed training process does not require precisely geometrically aligned patches.The source codes and trained weights are available at https://github.com/ducha-aiki/affnet
Open AccessRepeatability Is Not Enough: Learning Affine Regions via Discriminability
A method for learning local affine-covariant regions is presented. We show that maximizing geometric repeatability does not lead to local regions, a.k.a features,that are reliably matched and this necessitates descriptor-based learning. We explore factors that influence such learning and registration: the loss function, descriptor type, geometric parametrization and the trade-off between matchability and geometric accuracy and propose a novel hard negative-constant loss function for learning of affine regions. The affine shape estimator -- AffNet -- trained with the hard negative-constant loss outperforms the state-of-the-art in bag-of-words image retrieval and wide baseline stereo. The proposed training process does not require precisely geometrically aligned patches.The source codes and trained weights are available at https://github.com/ducha-aiki/affnet
- Top Cited Papers
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8183-8192
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss. DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem - object detection on (de-)blurred images. The method is 5 times faster than the closest competitor - Deep-Deblur [25]. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8183-8192
Top Cited PapersDeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss. DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem - object detection on (de-)blurred images. The method is 5 times faster than the closest competitor - Deep-Deblur [25]. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN.