Search Results for author:
Found 44 papers, 20 papers with code
Depth Assisted Full Resolution Network for Single Image-based View Synthesis
In this paper, we focus on a more challenging and ill-posed problem that is to synthesize novel viewpoints from one single input image.
Generating Adversarial Perturbation with Root Mean Square Gradient
We focus our attention on the problem of generating adversarial perturbations based on the gradient in image classification domain
Adaptive Gradient for Adversarial Perturbations Generation
Deep Neural Networks have achieved remarkable success in computer vision, natural language processing, and audio tasks.
Pixelation is NOT Done in Videos Yet
This paper introduces an algorithm to protect the privacy of individuals in streaming video data by blurring faces such that face cannot be reliably recognized.
Generating Minimal Adversarial Perturbations with Integrated Adaptive Gradients
Deep neural networks are easily fooled high confidence predictions for adversarial samples
Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
Thus, we address the problem of Image Harmonization: Given a spliced image and the mask of the spliced region, we try to harmonize the "style" of the pasted region with the background (non-spliced region).
Ranked #5 on
Image Harmonization
on HAdobe5k(1024$\times$1024)
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
With the help of novel masks or scenes, we enhance the current datasets using synthesized shadow images.
Ranked #2 on
Shadow Removal
on ISTD
Defocus Blur Detection via Depth Distillation
In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time.
Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal
Simultaneously, to increase the robustness of watermark, attacking technique, such as watermark removal, also gets the attention from the community.
News Image Steganography: A Novel Architecture Facilitates the Fake News Identification
A larger portion of fake news quotes untampered images from other sources with ulterior motives rather than conducting image forgery.
Privacy-sensitive Objects Pixelation for Live Video Streaming
With the prevailing of live video streaming, establishing an online pixelation method for privacy-sensitive objects is an urgency.
Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming
On the video live streaming dataset we collected, FPVLS obtains satisfying accuracy, real-time efficiency, and contains the over-pixelation problems.
Kinship Verification Based on Cross-Generation Feature Interaction Learning
Specifically, we take parents and children as a whole to extract the expressive local and non-local features.
Deep Collaborative Multi-Modal Learning for Unsupervised Kinship Estimation
To this end, we propose a novel deep collaborative multi-modal learning (DCML) to integrate the underlying information presented in facial properties in an adaptive manner to strengthen the facial details for effective unsupervised kinship verification.
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
To this end, we propose a novel spatial-separated curve rendering network(S$^2$CRNet) for efficient and high-resolution image harmonization for the first time.
Ranked #12 on
Image Harmonization
on iHarmony4
Learning Enriched Illuminants for Cross and Single Sensor Color Constancy
Color constancy aims to restore the constant colors of a scene under different illuminants.
Image Harmonization with Region-wise Contrastive Learning
Our method attempts to bring together corresponding positive and negative samples by maximizing the mutual information between the foreground and background styles, which desirably makes our harmonization network more robust to discriminate the foreground and background style features when harmonizing composite images.
Arbitrary Style Transfer with Structure Enhancement by Combining the Global and Local Loss
To solve this problem, we introduce a novel arbitrary style transfer method with structure enhancement by combining the global and local loss.
Asymmetric Scalable Cross-modal Hashing
In addition, most of the existing methods choose to use an $n\times n$ similarity matrix for optimization, which makes the memory and computation unaffordable.
ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal
Shadow removal improves the visual quality and legibility of digital copies of documents.
WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement
Image enhancement is a technique that frequently utilized in digital image processing.
A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement
In order to facilitate film-based image stylization research, we construct FilmSet, a large-scale and high-quality film style dataset.
Brain Diffuser: An End-to-End Brain Image to Brain Network Pipeline
Brain network analysis is essential for diagnosing and intervention for Alzheimer's disease (AD).
CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying
Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing.
Explicit Visual Prompting for Low-Level Structure Segmentations
Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i. e., the features from frozen patch embeddings and the input's high-frequency components.
Ranked #1 on
Salient Object Detection
on DUT-OMRON
Locality Preserving Multiview Graph Hashing for Large Scale Remote Sensing Image Search
This article proposes a multiview hashing with learnable parameters to retrieve the queried images for a large-scale remote sensing dataset.
Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation
In this paper, we introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet), with the aim to alleviate the computational burden of high-dimensional correlation tensor and explore internal latent interaction between query and support images by leveraging operations defined by the established quaternion algebra.
Ranked #19 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Multi-resolution Spatiotemporal Enhanced Transformer Denoising with Functional Diffusive GANs for Constructing Brain Effective Connectivity in MCI analysis
In this paper, a novel Multi-resolution Spatiotemporal Enhanced Transformer Denoising (MSETD) network with an adversarially functional diffusion model is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment (MCI) analysis.
Explicit Visual Prompting for Universal Foreground Segmentations
We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP).
Ranked #1 on
Salient Object Detection
on HKU-IS
DocDeshadower: Frequency-aware Transformer for Document Shadow Removal
In this study, we propose the DocDeshadower, a multi-frequency Transformer-based model built on Laplacian Pyramid.
AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition
Then these features are fed into a policy network to intelligently select a subsequence to process.
Ranked #6 on
Sign Language Recognition
on CSL-Daily
RBA-GCN: Relational Bilevel Aggregation Graph Convolutional Network for Emotion Recognition
This module can construct the interaction between different modalities and capture long-range contextual information based on similarity clusters.
Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer With Adaptive Channel Expansion
Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors.
High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net
We handle high-resolution document shadow removal directly via a larger-scale real-world dataset and a carefully designed frequency-aware network.
ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal
The STD module employs a traditional thresholding technique and leverages the attention mechanism of the Transformer to gather global information, thereby enabling precise detection of shadow masks.
MedPrompt: Cross-Modal Prompting for Multi-Task Medical Image Translation
Within this framework, we introduce the Prompt Extraction Block and the Prompt Fusion Block to efficiently encode the cross-modal prompt.
Perceptual MAE for Image Manipulation Localization: A High-level Vision Learner Focusing on Low-level Features
While MAE has demonstrated an impressive understanding of object semantics, PMAE can also compensate for low-level semantics with our proposed enhancements.
UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer
Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects.
ELF: An End-to-end Local and Global Multimodal Fusion Framework for Glaucoma Grading
Glaucoma is a chronic neurodegenerative condition that can lead to blindness.
Sketch Video Synthesis
Understanding semantic intricacies and high-level concepts is essential in image sketch generation, and this challenge becomes even more formidable when applied to the domain of videos.
GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging.
COMMA: Co-Articulated Multi-Modal Learning
First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated.
EmoSpeaker: One-shot Fine-grained Emotion-Controlled Talking Face Generation
Additionally, we propose an emotion intensity control method using a fine-grained emotion matrix.
Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
In this work, we introduce a test-time training (TTT) strategy to address the problem.
