DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

12 code implementations • CVPR 2018 • Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas

The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images.

Deblurring object-detection +1

Safe Augmentation: Learning Task-Specific Transformations from Data

1 code implementation • 30 Jul 2019 • Irynei Baran, Orest Kupyn, Arseny Kravchenko

We present a simple and explainable method called $\textbf{Safe Augmentation}$ that can learn task-specific data augmentation techniques that do not change the data distribution and improve the generalization of the model.

Data Augmentation

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

6 code implementations • ICCV 2019 • Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang

We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility.

Blind Face Restoration Generative Adversarial Network +4

Fast and Efficient Model for Real-Time Tiger Detection In The Wild

1 code implementation • 3 Sep 2019 • Orest Kupyn, Dmitry Pranchuk

The highest accuracy object detectors to date are based either on a two-stage approach such as Fast R-CNN or one-stage detectors such as Retina-Net or SSD with deep and complex backbones.

ActGAN: Flexible and Efficient One-shot Face Reenactment

no code implementations • 30 Mar 2020 • Ivan Kosarevych, Marian Petruk, Markian Kostiv, Orest Kupyn, Mykola Maksymenko, Volodymyr Budzan

We also introduce a solution to preserve a person's identity between synthesized and target person by adopting the state-of-the-art approach in deep face recognition domain.

Face Recognition Face Reenactment +1

FEAR: Fast, Efficient, Accurate and Robust Visual Tracker

1 code implementation • 15 Dec 2021 • Vasyl Borsuk, Roman Vei, Orest Kupyn, Tetiana Martyniuk, Igor Krashenyi, Jiři Matas

In addition, we expand the definition of the model efficiency by introducing FEAR benchmark that assesses energy consumption and execution speed.

Visual Object Tracking

DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image

1 code implementation • CVPR 2022 • Tetiana Martyniuk, Orest Kupyn, Yana Kurlyak, Igor Krashenyi, Jiři Matas, Viktoriia Sharmanska

Experimentally, DAD-3DNet outperforms or is comparable to the state-of-the-art models in (i) 3D Head Pose Estimation on AFLW2000-3D and BIWI, (ii) 3D Face Shape Reconstruction on NoW and Feng, and (iii) 3D Dense Head Alignment and 3D Landmarks Estimation on DAD-3DHeads dataset.

3D Reconstruction Head Pose Estimation