Search Results for author:
Found 27 papers, 13 papers with code
HPU: High-Bandwidth Processing Unit for Scalable, Cost-effective LLM Inference via GPU Co-processing
The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches.
Deep Polycuboid Fitting for Compact 3D Representation of Indoor Scenes
This paper presents a novel framework for compactly representing a 3D indoor scene using a set of polycuboids through a deep learning-based fitting method.
VisPath: Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven Optimization
Unprecedented breakthroughs in Large Language Models (LLMs) has amplified its penetration into application of automated visualization code generation.
Deep Cost Ray Fusion for Sparse Depth Video Completion
In this paper, we present a learning-based framework for sparse depth video completion.
Discontinuity-preserving Normal Integration with Auxiliary Edges
Using the auxiliary edges, we design a novel algorithm to optimize the discontinuity and the depth map from the input normal map.
Fashion Style Editing with Generative Human Prior
Image editing has been a long-standing challenge in the research community with its far-reaching impact on numerous applications.
Gyro-based Neural Single Image Deblurring
To handle gyro error, GyroDeblurNet is equipped with two novel neural network blocks: a gyro refinement block and a gyro deblurring block.
ParamISP: Learned Forward and Inverse ISPs using Camera Parameters
RAW images are rarely shared mainly due to its excessive data size compared to their sRGB counterparts obtained by camera ISPs.
Mesh Density Adaptation for Template-based Shape Reconstruction
In 3D shape reconstruction based on template mesh deformation, a regularization, such as smoothness energy, is employed to guide the reconstruction into a desirable direction.
Differentiable Display Photometric Stereo
In this paper, we present differentiable display photometric stereo (DDPS), addressing an often overlooked challenge in display photometric stereo: the design of display patterns.
Deep Deformable 3D Caricatures with Learned Shape Control
To achieve the goal, we propose an MLP-based framework for building a deformable surface model, which takes a latent code and produces a 3D surface.
Real-Time Video Deblurring via Lightweight Motion Compensation
While motion compensation greatly improves video deblurring quality, separately performing motion compensation and video deblurring demands huge computational overhead.
Reference-based Video Super-Resolution Using Multi-Camera Video Triplets
To facilitate the fusion and propagation of temporal reference features, we propose a propagative temporal fusion module.
Ranked #1 on
Reference-based Video Super-Resolution
on RealMCVSR
Reference-based Video Super-Resolution
Video Super-Resolution
MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
Based on the analysis, we propose Multi-Scale-Stage Network (MSSNet), a novel deep learning-based approach to single image deblurring that adopts our remedies to the defects.
Ranked #9 on
Deblurring
on RealBlur-J (trained on GoPro)
Realistic Blur Synthesis for Learning Image Deblurring
To this end, we present RSBlur, a novel dataset with real blurred images and the corresponding sharp image sequences to enable a detailed analysis of the difference between real and synthetic blur.
Ranked #1 on
Deblurring
on RSBlur (trained on synthetic)
Iterative Filter Adaptive Network for Single Image Defocus Deblurring
We propose a novel end-to-end learning-based approach for single image defocus deblurring.
Ranked #3 on
Image Defocus Deblurring
on RealDOF
Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes
To alleviate this problem, we propose two novel approaches to deblur videos by effectively aggregating information from multiple video frames.
Ranked #4 on
Deblurring
on Beam-Splitter Deblurring (BSD)
Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera
This paper presents an effective method for generating a spatiotemporal (time-varying) texture map for a dynamic object using a single RGB-D camera.
Deep Virtual Markers for Articulated 3D Shapes
We propose deep virtual markers, a framework for estimating dense and accurate positional information for various types of 3D data.
Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions
To utilize the property with inverse kernels, we exploit the observation that when only the size of a defocus blur changes while keeping the shape, the shape of the corresponding inverse kernel remains the same and only the scale changes.
Ranked #8 on
Image Defocus Deblurring
on DPD
StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation
Our framework, dubbed StyleCariGAN, automatically creates a realistic and detailed caricature from an input photo with optional controls on shape exaggeration degree and color stylization type.
Deep Color Transfer using Histogram Analogy
We propose a novel approach to transferring the color of a reference image to a given source image.
NPRportrait 1.0: A Three-Level Benchmark for Non-Photorealistic Rendering of Portraits
Despite the recent upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer, the state of performance evaluation in this field is limited, especially compared to the norms in the computer vision and machine learning communities.
SRFeat: Single Image Super-Resolution with Feature Discrimination
Generative adversarial networks (GANs) have recently been adopted to single image super resolution (SISR) and showed impressive results with realistically synthesized high-frequency textures.
Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN
Raw depth images captured by consumer depth cameras suffer from noisy and missing values.
RDFNet: RGB-D Multi-Level Residual Feature Fusion for Indoor Semantic Segmentation
Feature fusion blocks learn residual RGB and depth features and their combinations to fully exploit the complementary characteristics of RGB and depth data.
Ranked #35 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
Convergence Analysis of MAP based Blur Kernel Estimation
One popular approach for blind deconvolution is to formulate a maximum a posteriori (MAP) problem with sparsity priors on the gradients of the latent image, and then alternatingly estimate the blur kernel and the latent image.
