Search Results for author:
Found 34 papers, 18 papers with code
Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation
Accurately estimating the pose of an object is a crucial task in computer vision and robotics.
LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction
In this paper, we propose an end-to-end HDR video composition framework, which aligns LDR frames in the feature space and then merges aligned features into an HDR frame, without relying on pixel-domain optical flow.
High Dynamic Range Imaging of Dynamic Scenes with Saturation Compensation but without Explicit Motion Compensation
For HDR imaging, some methods capture multiple low dynamic range (LDR) images with altering exposures to aggregate more information.
Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network
There have been many image denoisers using deep neural networks, which outperform conventional model-based methods by large margins.
Lightweight Hybrid Video Compression Framework Using Reference-Guided Restoration Network
The decoder is constructed with corresponding video/image decoders and a new restoration network, which enhances the compressed video in two-step processes.
Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation
Specifically, the framework comprises two models: a predictive model that infers an optimal objective map for a given low-resolution (LR) input and a generative model that applies a target objective map to produce the corresponding SR output.
Ranked #1 on
Image Super-Resolution
on DIV2K val - 4x upscaling
Training Patch Analysis and Mining Skills for Image Restoration Deep Neural Networks
Eventually, we propose a guideline for the patch extraction from given training images.
Variational Deep Image Restoration
This paper presents a new variational inference framework for image restoration and a convolutional neural network (CNN) structure that can solve the restoration problems described by the proposed framework.
One-Shot Face Reenactment on Megapixels
The goal of face reenactment is to transfer a target expression and head pose to a source face while preserving the source identity.
Flexible Style Image Super-Resolution using Conditional Objective
Instead of using multiple models, we present a more efficient method to train a single adjustable SR model on various combinations of losses by taking advantage of multi-task learning.
Ranked #1 on
Image Super-Resolution
on General100 - 8x upscaling
Deep Hash Distillation for Image Retrieval
To mitigate this issue, data augmentation can be applied during training.
DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation
Our pose estimation method, dynamic projective spatial transformer network (DProST), localizes the region of interest grid on the rays in camera space and transforms the grid to object space by estimated pose.
LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Network
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms.
A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution
We also propose a residual self-attention (RSA) module to further boost the performance, which produces 3-dimensional attention maps without additional parameters by cooperating with residual structures.
Self-supervised Product Quantization for Deep Unsupervised Image Retrieval
Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems.
Similarity Guided Deep Face Image Retrieval
Face image retrieval, which searches for images of the same identity from the query input face image, is drawing more attention as the size of the image database increases rapidly.
Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS
The recent progress of deep convolutional neural networks has enabled great success in single image super-resolution (SISR) and many other vision tasks.
Variational Deep Image Denoising
These methods separate the original problem into easier sub-problems and thus have shown improved performance than the naively trained CNN.
Deep Universal Blind Image Denoising
Traditionally, many researchers have investigated image priors for the denoising, within the Bayesian perspective based on image properties and statistics.
Meta-Transfer Learning for Zero-Shot Super-Resolution
Despite their remarkable performance based on the external dataset, they cannot exploit internal information within a specific image.
Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization
Real-noise denoising is a challenging task because the statistics of real-noise do not follow the normal distribution, and they are also spatially and temporally changing.
Ranked #11 on
Image Denoising
on DND
(using extra training data)
Generalized Product Quantization Network for Semi-supervised Image Retrieval
Image retrieval methods that employ hashing or vector quantization have achieved great success by taking advantage of deep learning.
Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation
The two-stream fusion network again consists of motion and appearance stream networks, which extract long-term temporal and spatial information, respectively.
Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination
Recently, many convolutional neural networks for single image super-resolution (SISR) have been proposed, which focus on reconstructing the high-resolution images in terms of objective distortion measures.
Distill-2MD-MTL: Data Distillation based on Multi-Dataset Multi-Domain Multi-Task Frame Work to Solve Face Related Tasksks, Multi Task Learning, Semi-Supervised Learning
We propose a new semi-supervised learning method on face-related tasks based on Multi-Task Learning (MTL) and data distillation.
Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network
For training our network, we develop a cross-entropy based loss function that addresses the imbalance problems.
Joint High Dynamic Range Imaging and Super-Resolution from a Single Image
This paper presents a new framework for jointly enhancing the resolution and the dynamic range of an image, i. e., simultaneous super-resolution (SR) and high dynamic range imaging (HDRI), based on a convolutional neural network (CNN).
PuVAE: A Variational Autoencoder to Purify Adversarial Examples
Deep neural networks are widely used and exhibit excellent performance in many areas.
Ranked #2 on
Adversarial Defense against FGSM Attack
on MNIST
Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks
In this paper, we show that finding an appropriate feature for the given problem may be still important as they can en- hance the performance of CNN-based algorithms.
Generation of High Dynamic Range Illumination from a Single Image for the Enhancement of Undesirably Illuminated Images
This paper presents an algorithm that enhances undesirably illuminated images by generating and fusing multi-level illuminations from a single image. The input image is first decomposed into illumination and reflectance components by using an edge-preserving smoothing filter.
Co-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph
We utilize deep saliency networks to transfer co-saliency prior knowledge and better capture high-level semantic information, and the resulting initial co-saliency maps are enhanced by seed propagation steps over an integrated graph.
Self-Committee Approach for Image Restoration Problems using Convolutional Neural Network
There have been many discriminative learning methods using convolutional neural networks (CNN) for several image restoration problems, which learn the mapping function from a degraded input to the clean output.
Block-Matching Convolutional Neural Network for Image Denoising
There are two main streams in up-to-date image denoising algorithms: non-local self similarity (NSS) prior based methods and convolutional neural network (CNN) based methods.
A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction
From these observations, for enjoying the performance of inception-like structure on the image based problems we propose a new convolutional network-in-network structure.
