Search Results for author:
Found 43 papers, 22 papers with code
Towards Better Adversarial Purification via Adversarial Denoising Diffusion Training
Empirical results show that ADDT improves the robustness of DBP models.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results
This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained.
Boosting Image Restoration via Priors from Pre-trained Models
Pre-trained models with large-scale training data, such as CLIP and Stable Diffusion, have demonstrated remarkable performance in various high-level computer vision tasks such as image understanding and generation from language descriptions.
Learning to Remove Wrinkled Transparent Film with Polarized Prior
We aim to remove interference from the film (specular highlights and other degradations) with an end-to-end framework.
UniMODE: Unified Monocular 3D Object Detection
To address these challenges, we build a detector based on the bird's-eye-view (BEV) detection paradigm, where the explicit feature projection is beneficial to addressing the geometry learning ambiguity when employing multiple scenarios of data to train detectors.
Diving Deep into Regions: Exploiting Regional Information Transformer for Single Image Deraining
Our RTB is used for attention selection of rain-affected and unaffected regions and local modeling of mixed scales.
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error.
Ranked #3 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
Video Frame Interpolation with Region-Distinguishable Priors from SAM
In existing Video Frame Interpolation (VFI) approaches, the motion estimation between neighboring frames plays a crucial role.
Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance
First, a depth-aware feature extraction module is designed to inject depth priors into the image representation.
Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Network
To address this, we present a Self-Supervised Learning (SSL) technique tailored as an auxiliary loss for any 3D-GAN, designed to improve its 3D geometrical modeling capabilities.
An Incremental Unified Framework for Small Defect Inspection
Artificial Intelligence (AI)-driven defect inspection is pivotal in industrial manufacturing.
CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
We present CorresNeRF, a novel method that leverages image correspondence priors computed by off-the-shelf methods to supervise NeRF training.
Diffusion Noise Feature: Accurate and Fast Generated Image Detection
DNF is extracted from the estimated noise generated during the inverse diffusion process.
Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction
This paper introduces RDA, a pioneering approach designed to address two primary deficiencies prevalent in previous endeavors aiming at stealing pre-trained encoders: (1) suboptimal performances attributed to biased optimization objectives, and (2) elevated query costs stemming from the end-to-end paradigm that necessitates querying the target encoder every epoch.
Clarity ChatGPT: An Interactive and Adaptive Processing System for Image Restoration and Enhancement
The generalization capability of existing image restoration and enhancement (IRE) methods is constrained by the limited pre-trained datasets, making it difficult to handle agnostic inputs such as different degradation levels and scenarios beyond their design scopes.
LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios.
Application of a Dense Fusion Attention Network in Fault Diagnosis of Centrifugal Fan
However, it is still a challenge to understand the correspondence between the structure and function of the model and the diagnosis process.
FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
Then, we investigate the role of synthetic images by joint training with real images, or pre-training for real images.
SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning
Self-supervised learning (SSL), a paradigm harnessing unlabeled datasets to train robust encoders, has recently witnessed substantial success.
High Dynamic Range Image Reconstruction via Deep Explicit Polynomial Curve Estimation
Besides, since all current datasets do not provide the corresponding relationship between the tone mapping function and the LDR image, we construct a new dataset with both synthetic and real images.
Lighting up NeRF via Unsupervised Decomposition and Enhancement
Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene.
Low-Light Image Enhancement via Structure Modeling and Guidance
Moreover, to improve the appearance modeling, which is implemented with a simple U-Net, a novel structure-guided enhancement module is proposed with structure-guided feature synthesis layers.
Leaf Cultivar Identification via Prototype-enhanced Learning
Plant leaf identification is crucial for biodiversity protection and conservation and has gradually attracted the attention of academia in recent years.
TriVol: Point Cloud Rendering via Triple Volumes
However, artifacts still appear in rendered images, due to the challenges in extracting continuous and discriminative 3D features from point clouds.
Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields
Also, we present Point Encoding to build Multi-scale Radiance Fields that provide discriminative 3D point features.
Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation
In this paper, we propose a novel framework that enhances the fidelity of human face inversion by designing a new module to decompose the input images to ID and OOD partitions with invertibility masks.
General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments
In this paper, we use Deep Generative Networks (DGNs) with a novel training mechanism to eliminate the distribution gap.
S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention
Transformer's recent integration into style transfer leverages its proficiency in establishing long-range dependencies, albeit at the expense of attenuated local modeling.
Local Low-light Image Enhancement via Region-Aware Normalization
RANLEN uses a dynamically designed mask-based normalization operation, which enhances an image in a spatially varying manner, ensuring that the enhancement results are consistent with the requirements specified by the input mask.
DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation
Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations.
Universal Adaptive Data Augmentation
Different from existing methods, UADA would adaptively update DA's parameters according to the target model's gradient information during training: given a pre-defined set of DA operations, we randomly decide types and magnitudes of DA operations for every data batch during training, and adaptively update DA's parameters along the gradient direction of the loss concerning DA's parameters.
Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy.
Towards Real-World Video Denosing: A Practical Video Denosing Dataset and Network
Moreover, we also propose a new video denoising framework, called Recurrent Video Denoising Transformer (RVDT), which can achieve SOTA performance on PVDD and other current video denoising benchmarks.
How Well Do Self-Supervised Methods Perform in Cross-Domain Few-Shot Learning?
In this paper, we investigate the role of self-supervised representation learning in the context of CDFSL via a thorough evaluation of existing methods.
SNR-Aware Low-Light Image Enhancement
They are long-range operations for image regions of extremely low Signal-to-Noise-Ratio (SNR) and short-range operations for other regions.
Ranked #2 on
Low-Light Image Enhancement
on LIME
Adversarial Attacks on ML Defense Models Competition
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.
Conditional Temporal Variational AutoEncoder for Action Video Prediction
To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video.
Self-Supervised 3D Mesh Reconstruction From Single Images
Recent single-view 3D reconstruction methods reconstruct object's shape and texture from a single image with only 2D image-level annotation.
Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment
Low-light video enhancement is an important task.
General Adversarial Defense via Pixel Level and Feature Level Distribution Alignment
Specifically, compared with previous methods, we propose a more efficient pixel-level training constraint to weaken the hardness of aligning adversarial samples to clean samples, which can thus obviously enhance the robustness on adversarial samples.
Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation
Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task.
View Independent Generative Adversarial Network for Novel View Synthesis
Synthesizing novel views from a 2D image requires to infer 3D structure and project it back to 2D from a new viewpoint.
