Search Results for author:
Found 45 papers, 22 papers with code
Bézier Splatting for Fast and Differentiable Vector Graphics
Differentiable vector graphics (VGs) are widely used in image vectorization and vector synthesis, while existing representations are costly to optimize and struggle to achieve high-quality rendering results for high-resolution images.
Latent Radiance Fields with 3D-aware 2D Representations
The framework consists of three stages: (1) a correspondence-aware autoencoding method that enhances the 3D consistency of 2D latent representations, (2) a latent radiance field (LRF) that lifts these 3D-aware 2D representations into 3D space, and (3) a VAE-Radiance Field (VAE-RF) alignment strategy that improves image decoding from the rendered 2D representations.
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient pipelines.
AutoAL: Automated Active Learning with Differentiable Query Strategy Search
AutoAL consists of two neural nets, named SearchNet and FitNet, which are optimized concurrently under a differentiable bi-level optimization framework.
Fundus to Fluorescein Angiography Video Generation as a Retinal Generative Foundation Model
Fundus fluorescein angiography (FFA) is crucial for diagnosing and monitoring retinal vascular issues but is limited by its invasive nature and restricted accessibility compared to color fundus (CF) imaging.
Multimodal Generalized Category Discovery
Generalized Category Discovery (GCD) aims to classify inputs into both known and novel categories, a task crucial for open-world scientific discoveries.
SoftShadow: Leveraging Penumbra-Aware Soft Masks for Shadow Removal
In view of this, inspired by the physical model of shadow formation, we introduce novel soft shadow masks specifically designed for shadow removal.
EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis
Early detection of eye diseases like glaucoma, macular degeneration, and diabetic retinopathy is crucial for preventing vision loss.
Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance
In this work, we pioneer dynamic FFA video generation from static CF images.
Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey
In this paper, we are the first to provide a comprehensive survey to cover various aspects ranging from technical details to applications.
Learning Gaze-aware Compositional GAN
In this work, we present a generative framework to create annotated gaze data by leveraging the benefits of labeled and unlabeled data sources.
EyeFound: A Multimodal Generalist Foundation Model for Ophthalmic Imaging
EyeFound provides a generalizable solution to improve model performance and lessen the annotation burden on experts, facilitating widespread clinical AI applications for retinal imaging.
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
Diffusion models have proven to be highly effective in image and video generation; however, they still face composition challenges when generating images of varying sizes due to single-scale training data.
S$^3$-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation
Deep-learning models have been successful in biomedical image segmentation.
MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
In this work, we study a novel self-supervised pre-training pipeline, namely Multi-task Self-super-vised Continual Learning (MUSCLE), for multiple medical imaging tasks, such as classification and segmentation, using X-ray images collected from multiple body parts, including heads, lungs, and bones.
Domain-Scalable Unpaired Image Translation via Latent Space Anchoring
However, given a UNIT model trained on certain domains, it is difficult for current methods to incorporate new domains because they often need to train the full model on both existing and new domains.
ShadowFormer: Global Context Helps Image Shadow Removal
It is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions.
Ranked #1 on
Shadow Removal
on ISTD
Temporal Output Discrepancy for Loss Estimation-based Active Learning
Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this paper we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss.
QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity
The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to push the generated image toward high similarities in both content and style.
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
Recent deep learning methods have achieved promising results in image shadow removal.
Ranked #9 on
Shadow Removal
on ISTD+
Making Your First Choice: To Address Cold Start Problem in Vision Active Learning
However, we uncover a striking contradiction to this promise: active learning fails to select data as efficiently as random selection at the first few choices.
Instance Segmentation of Unlabeled Modalities via Cyclic Segmentation GAN
Instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming.
Boosting Active Learning via Improving Test Performance
In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance.
FINO: Flow-based Joint Image and Noise Model
One of the fundamental challenges in image restoration is denoising, where the objective is to estimate the clean image from its noisy measurements.
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Most of the existing contrastive learning methods employ pre-defined view generation methods, e. g., node drop or edge perturbation, which usually cannot adapt to input data or preserve the original semantic structures well.
Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification.
Semi-Supervised Active Learning with Temporal Output Discrepancy
To lower the cost of data annotation, active learning has been proposed to interactively query an oracle to annotate a small proportion of informative samples in an unlabeled dataset.
ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
Low-light image enhancement (LLIE) is a pervasive yet challenging problem, since: 1) low-light measurements may vary due to different imaging conditions in practice; 2) images can be enlightened subjectively according to diverse preferences by each individual.
Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContRE adopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the generalization performance of deep models in complement with a testing set.
BM-NAS: Bilevel Multimodal Neural Architecture Search
Deep neural networks (DNNs) have shown superior performances on various multimodal learning problems.
ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
The forward inference projects input images into deep features, while the backward inference remaps deep features back to input images in a lossless and unbiased way.
Democratizing Evaluation of Deep Model Interpretability through Consensus
Given any task/dataset, Consensus first obtains the interpretation results using existing tools, e. g., LIME (Ribeiro et al., 2016), for every model in the committee, then aggregates the results from the entire committee and approximates the “ground truth” of interpretations through voting.
Dual Low-Rank Multimodal Fusion
Tensor-based fusion methods have been proven effective in multimodal fusion tasks.
Contour Primitive of Interest Extraction Network Based on One-Shot Learning for Object-Agnostic Vision Measurement
For the novel CPI extraction task, we built the Object Contour Primitives dataset using online public images, and the Robotic Object Contour Measurement dataset using a camera mounted on a robot.
TP-LSD: Tri-Points Based Line Segment Detector
To realize one-step detection with a faster and more compact model, we introduce the tri-points representation, converting the line segment detection to the end-to-end prediction of a root-point and two endpoints for each line segment.
Ranked #6 on
Line Segment Detection
on York Urban Dataset
SBAT: Video Captioning with Sparse Boundary-Aware Transformer
However, video captioning is a multimodal learning problem, and the video features have much redundancy between different time steps.
Generating Person Images with Appearance-aware Pose Stylizer
Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e. g., appearance, pose, foreground, background, local details, global structures, etc.
Effects of Regional Trade Agreement to Local and Global Trade Purity Relationships
In addition, we apply the network to reflect the purity of the trade relations among countries.
Parameter-Free Style Projection for Arbitrary Style Transfer
This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs.
Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
This paper addresses the challenging task of video captioning which aims to generate descriptions for video data.
Text Guided Person Image Synthesis
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions.
Perceiving Physical Equation by Observing Visual Scenarios
To tackle this challenge, we present a novel pipeline comprised of an Observer Engine and a Physicist Engine by respectively imitating the actions of an observer and a physicist in the real world.
Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity.
GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
A key problem in deep multi-attribute learning is to effectively discover the inter-attribute correlation structures.
Deep Learning Driven Visual Path Prediction from a Single Image
The highly effective visual representation and deep context models ensure that our framework makes a deep semantic understanding of the scene and motion pattern, consequently improving the performance of the visual path prediction task.
