Search Results for author:
Found 40 papers, 14 papers with code
SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
We categorize the key skeletal-temporal relations for action recognition into a total of four distinct types.
Ranked #1 on
Skeleton Based Action Recognition
on N-UCLA
FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring
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.
DyBluRF: Dynamic Deblurring Neural Radiance Fields for Blurry Monocular Video
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.
From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior
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.
ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields
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.
Novel View Synthesis with View-Dependent Effects from a Single Image
In this paper, we firstly consider view-dependent effects into single image-based novel view synthesis (NVS) problems.
COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability
Recently, neural network (NN)-based image compression studies have actively been made and has shown impressive performance in comparison to traditional methods.
Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer
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.
Selective compression learning of latent representations for variable-rate image compression
For this, we first generate a 3D importance map as the nature of input content to represent the underlying importance of the representation elements.
Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based bokeh effect rendering approach that can run on modern smartphone GPUs using TensorFlow Lite.
Layered Depth Refinement with Mask Guidance
Depth maps are used in a wide range of applications from 3D rendering to 2D image effects such as Bokeh.
Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos
Recently, much attention has been drawn to learning the underlying 3D structures of a scene from monocular videos in a fully self-supervised fashion.
DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
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).
SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery
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
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.
XVFI: eXtreme Video Frame Interpolation
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.
PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
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.
PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss
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.
Zoom-to-Inpaint: Image Inpainting with High-Frequency Details
Although deep learning has enabled a huge leap forward in image inpainting, current methods are often unable to synthesize realistic high-frequency details.
KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment
Blind super-resolution (SR) methods aim to generate a high quality high resolution image from a low resolution image containing unknown degradations.
Ranked #3 on
Blind Super-Resolution
on DIV2KRK - 2x upscaling
Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes
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.
NTIRE 2020 Challenge on NonHomogeneous Dehazing
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
Deep 3D Pan via Local adaptive "t-shaped" convolutions with global and local adaptive dilations
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.
An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization
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.
Deep 3D Pan via adaptive "t-shaped" convolutions with global and local adaptive dilations
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.
Analysis and Interpretation of Deep CNN Representations as Perceptual Quality Features
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.
Deep 3D-Zoom Net: Unsupervised Learning of Photo-Realistic 3D-Zoom
The 3D-zoom operation is the positive translation of the camera in the Z-axis, perpendicular to the image plane.
JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video
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.
S3: A Spectral-Spatial Structure Loss for Pan-Sharpening Networks
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 Predictive Video Compression with Bi-directional Prediction
Learned from the lesson of the conventional video coding, a B-frame coding structure is incorporated in our BP-DVC Net.
A HVS-inspired Attention to Improve Loss Metrics for CNN-based Perception-Oriented Super-Resolution
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.
A Novel Monocular Disparity Estimation Network with Domain Transformation and Ambiguity Learning
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.
A Novel Just-Noticeable-Difference-based Saliency-Channel Attention Residual Network for Full-Reference Image Quality Predictions
Recently, due to the strength of deep convolutional neural networks (CNN), many CNN-based image quality assessment (IQA) models have been studied.
3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks
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.
Why Are Deep Representations Good Perceptual Quality Features?
In particular, we focus our analysis on fundamental aspects of human perception, such as the contrast sensitivity and orientation selectivity.
Finding Correspondences for Optical Flow and Disparity Estimations using a Sub-pixel Convolution-based Encoder-Decoder Network
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.
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
Single Image Super-Resolution Using Lightweight CNN with Maxout Units
To the best of our knowledge, we are the first to incorporate MU into SR applications and show promising performance results.
