Search Results for author: Munchurl Kim

Found 40 papers, 14 papers with code

FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring

no code implementations CVPR 2024 Geunhyuk Youk, Jihyong Oh, Munchurl Kim

In this paper, we propose a novel flow-guided dynamic filtering (FGDF) and iterative feature refinement with multi-attention (FRMA), which constitutes our VSRDB framework, denoted as FMA-Net.

Deblurring Representation Learning +1

DyBluRF: Dynamic Deblurring Neural Radiance Fields for Blurry Monocular Video

no code implementations21 Dec 2023 Minh-Quan Viet Bui, Jongmin Park, Jihyong Oh, Munchurl Kim

In response, we propose a novel dynamic deblurring NeRF framework for blurry monocular video, called DyBluRF, consisting of a Base Ray Initialization (BRI) stage and a Motion Decomposition-based Deblurring (MDD) stage.

Deblurring Novel View Synthesis

From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior

no code implementations CVPR 2024 Jaeho Moon, Juan Luis Gonzalez Bello, Byeongjun Kwon, Munchurl Kim

Subsequently, in the fine training stage, we refine the DE network to learn the detailed depth of the objects from the reprojection loss, while ensuring accurate DE on the moving object regions by employing our regularization loss with a cost-volume-based weighting factor.

Monocular Depth Estimation

ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields

no code implementations13 Dec 2023 Juan Luis Gonzalez Bello, Minh-Quan Viet Bui, Munchurl Kim

Recent advances in neural rendering have shown that, albeit slow, implicit compact models can learn a scene's geometries and view-dependent appearances from multiple views.

Neural Rendering

COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability

no code implementations ICCV 2023 Jongmin Park, Jooyoung Lee, Munchurl Kim

Recently, neural network (NN)-based image compression studies have actively been made and has shown impressive performance in comparison to traditional methods.

Image Compression

Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer

no code implementations CVPR 2023 Agus Gunawan, Soo Ye Kim, Hyeonjun Sim, Jae-Ho Lee, Munchurl Kim

In order to modernize old photos, we propose a novel multi-reference-based old photo modernization (MROPM) framework consisting of a network MROPM-Net and a novel synthetic data generation scheme.

Style Transfer Synthetic Data Generation

Selective compression learning of latent representations for variable-rate image compression

1 code implementation8 Nov 2022 Jooyoung Lee, Seyoon Jeong, Munchurl Kim

For this, we first generate a 3D importance map as the nature of input content to represent the underlying importance of the representation elements.

Image Compression

Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos

no code implementations18 May 2022 Juan Luis Gonzalez Bello, Jaeho Moon, Munchurl Kim

Recently, much attention has been drawn to learning the underlying 3D structures of a scene from monocular videos in a fully self-supervised fashion.

Depth Estimation Quantization

DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting

1 code implementation19 Nov 2021 Jihyong Oh, Munchurl Kim

In this paper, we propose a novel joint deblurring and multi-frame interpolation (DeMFI) framework, called DeMFI-Net, which accurately converts blurry videos of lower-frame-rate to sharp videos at higher-frame-rate based on flow-guided attentive-correlation-based feature bolstering (FAC-FB) module and recursive boosting (RB), in terms of multi-frame interpolation (MFI).

Deblurring Video Enhancement +2

SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery

1 code implementation CVPR 2021 Jaehyup Lee, Soomin Seo, Munchurl Kim

Pan-sharpening is a process of merging a high-resolution (HR) panchromatic (PAN) image and its corresponding low-resolution (LR) multi-spectral (MS) image to create an HR-MS and pan-sharpened image.

Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images

no code implementations16 Apr 2021 Dac Tung Vu, Juan Luis Gonzalez, Munchurl Kim

In this work, we propose a novel network architecture consisting of three sub-networks to remove heavy rain from a single image without estimating rain streaks and fog separately.

Single Image Deraining

XVFI: eXtreme Video Frame Interpolation

1 code implementation ICCV 2021 Hyeonjun Sim, Jihyong Oh, Munchurl Kim

In this paper, we firstly present a dataset (X4K1000FPS) of 4K videos of 1000 fps with the extreme motion to the research community for video frame interpolation (VFI), and propose an extreme VFI network, called XVFI-Net, that first handles the VFI for 4K videos with large motion.

4k eXtreme-Video-Frame-Interpolation +1

PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier

no code implementations29 Mar 2021 Jihyong Oh, Munchurl Kim

In this paper, we firstly propose a novel GAN-based multi-task learning (MTL) method for SAR target image generation, called PeaceGAN that uses both pose angle and target class information, which makes it possible to produce SAR target images of desired target classes at intended pose angles.

Image Generation Multi-Task Learning

PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss

1 code implementation CVPR 2021 Juan Luis Gonzalez Bello, Munchurl Kim

Our PLADE-Net is based on a new network architecture with neural positional encoding and a novel loss function that borrows from the closed-form solution of the matting Laplacian to learn pixel-level accurate depth estimation from stereo images.

Depth Estimation Image Matting

Zoom-to-Inpaint: Image Inpainting with High-Frequency Details

1 code implementation17 Dec 2020 Soo Ye Kim, Kfir Aberman, Nori Kanazawa, Rahul Garg, Neal Wadhwa, Huiwen Chang, Nikhil Karnad, Munchurl Kim, Orly Liba

Although deep learning has enabled a huge leap forward in image inpainting, current methods are often unable to synthesize realistic high-frequency details.

Image Inpainting Super-Resolution +1

KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment

1 code implementation CVPR 2021 Soo Ye Kim, Hyeonjun Sim, Munchurl Kim

Blind super-resolution (SR) methods aim to generate a high quality high resolution image from a low resolution image containing unknown degradations.

Blind Super-Resolution Super-Resolution

Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes

1 code implementation NeurIPS 2020 Juan Luis Gonzalez, Munchurl Kim

However, previous methods usually learn forward or backward image synthesis, but not depth estimation, as they cannot effectively neglect occlusions between the target and the reference images.

Depth Estimation Image Generation

Deep 3D Pan via Local adaptive "t-shaped" convolutions with global and local adaptive dilations

no code implementations ICLR 2020 Juan Luis Gonzalez Bello, Munchurl Kim

Our proposed network architecture, the monster-net, is devised with a novel t-shaped adaptive kernel with globally and locally adaptive dilation, which can efficiently incorporate global camera shift into and handle local 3D geometries of the target image's pixels for the synthesis of naturally looking 3D panned views when a 2-D input image is given.

Monocular Depth Estimation SSIM +1

An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization

1 code implementation30 Dec 2019 Jooyoung Lee, Seunghyun Cho, Munchurl Kim

In order to show the effectiveness of our proposed JointIQ-Net, extensive experiments have been performed, and showed that the JointIQ-Net achieves a remarkable performance improvement in coding efficiency in terms of both PSNR and MS-SSIM, compared to the previous learned image compression methods and the conventional codecs such as VVC Intra (VTM 7. 1), BPG, and JPEG2000.

Image Compression MS-SSIM +1

FISR: Deep Joint Frame Interpolation and Super-Resolution with a Multi-scale Temporal Loss

1 code implementation16 Dec 2019 Soo Ye Kim, Jihyong Oh, Munchurl Kim

In this paper, we first propose a joint VFI-SR framework for up-scaling the spatio-temporal resolution of videos from 2K 30 fps to 4K 60 fps.

2k 4k +4

Deep 3D Pan via adaptive "t-shaped" convolutions with global and local adaptive dilations

no code implementations2 Oct 2019 Juan Luis Gonzalez Bello, Munchurl Kim

Our proposed network architecture, the monster-net, is devised with a novel "t-shaped" adaptive kernel with globally and locally adaptive dilation, which can efficiently incorporate global camera shift into and handle local 3D geometries of the target image's pixels for the synthesis of naturally looking 3D panned views when a 2-D input image is given.

Monocular Depth Estimation SSIM +1

Analysis and Interpretation of Deep CNN Representations as Perceptual Quality Features

no code implementations25 Sep 2019 Taimoor Tariq, Munchurl Kim

In this paper, to get more insight, we link basic human visual perception to characteristics of learned deep CNN representations as a novel and first attempt to interpret them.

Image Quality Assessment Image Restoration +4

Deep 3D-Zoom Net: Unsupervised Learning of Photo-Realistic 3D-Zoom

no code implementations20 Sep 2019 Juan Luis Gonzalez Bello, Munchurl Kim

The 3D-zoom operation is the positive translation of the camera in the Z-axis, perpendicular to the image plane.

Disparity Estimation Novel View Synthesis +1

JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video

1 code implementation10 Sep 2019 Soo Ye Kim, Jihyong Oh, Munchurl Kim

Joint learning of super-resolution (SR) and inverse tone-mapping (ITM) has been explored recently, to convert legacy low resolution (LR) standard dynamic range (SDR) videos to high resolution (HR) high dynamic range (HDR) videos for the growing need of UHD HDR TV/broadcasting applications.

Image Reconstruction Inverse-Tone-Mapping +2

S3: A Spectral-Spatial Structure Loss for Pan-Sharpening Networks

no code implementations13 Jun 2019 Jae-Seok Choi, Yongwoo Kim, Munchurl Kim

Our proposed S3 loss can be very effectively utilized for pan-sharpening with various types of CNN structures, resulting in significant visual improvements on PS images with suppressed artifacts.

Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications

1 code implementation ICCV 2019 Soo Ye Kim, Jihyong Oh, Munchurl Kim

Joint SR and ITM is an intricate task, where high frequency details must be restored for SR, jointly with the local contrast, for ITM.

4k 8k +4

Deep Predictive Video Compression with Bi-directional Prediction

no code implementations5 Apr 2019 Woonsung Park, Munchurl Kim

Learned from the lesson of the conventional video coding, a B-frame coding structure is incorporated in our BP-DVC Net.

Decoder Image Compression +4

A HVS-inspired Attention to Improve Loss Metrics for CNN-based Perception-Oriented Super-Resolution

no code implementations30 Mar 2019 Taimoor Tariq, Juan Luis Gonzalez, Munchurl Kim

We identify regions in input images, based on the underlying spatial frequency, which are not generally well reconstructed during Super-Resolution but are most important in terms of visual sensitivity.

Image Restoration Super-Resolution

A Novel Monocular Disparity Estimation Network with Domain Transformation and Ambiguity Learning

no code implementations20 Mar 2019 Juan Luis Gonzalez Bello, Munchurl Kim

Convolutional neural networks (CNN) have shown state-of-the-art results for low-level computer vision problems such as stereo and monocular disparity estimations, but still, have much room to further improve their performance in terms of accuracy, numbers of parameters, etc.

Decoder Disparity Estimation +2

A Novel Just-Noticeable-Difference-based Saliency-Channel Attention Residual Network for Full-Reference Image Quality Predictions

no code implementations14 Feb 2019 Soomin Seo, Sehwan Ki, Munchurl Kim

Recently, due to the strength of deep convolutional neural networks (CNN), many CNN-based image quality assessment (IQA) models have been studied.

Image Quality Assessment

3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks

1 code implementation21 Dec 2018 Soo Ye Kim, Jeongyeon Lim, Taeyoung Na, Munchurl Kim

In video super-resolution, the spatio-temporal coherence between, and among the frames must be exploited appropriately for accurate prediction of the high resolution frames.

Video Super-Resolution

Why Are Deep Representations Good Perceptual Quality Features?

no code implementations ECCV 2020 Taimoor Tariq, Okan Tarhan Tursun, Munchurl Kim, Piotr Didyk

In particular, we focus our analysis on fundamental aspects of human perception, such as the contrast sensitivity and orientation selectivity.

Image Quality Assessment Image Reconstruction +5

Finding Correspondences for Optical Flow and Disparity Estimations using a Sub-pixel Convolution-based Encoder-Decoder Network

no code implementations7 Oct 2018 Juan Luis Gonzalez, Muhammad Sarmad, Hyunjoo J. Lee, Munchurl Kim

We show a supervised end-to-end training of our proposed networks for optical flow and disparity estimations, and an unsupervised end-to-end training for monocular depth and pose estimations.

Decoder Disparity Estimation +1

Single Image Super-Resolution Using Lightweight CNN with Maxout Units

no code implementations7 Nov 2017 Jae-Seok Choi, Munchurl Kim

To the best of our knowledge, we are the first to incorporate MU into SR applications and show promising performance results.

Image Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.