Search Results for author:
Found 87 papers, 42 papers with code
Geometric Estimation via Robust Subspace Recovery
Geometric estimation from image point correspondences is the core procedure of many 3D vision problems, which is prevalently accomplished by random sampling techniques.
CALLIC: Content Adaptive Learning for Lossless Image Compression
To address this challenge, we explore the connection between the Minimum Description Length (MDL) principle and Parameter-Efficient Transfer Learning (PETL), leading to the development of a novel content-adaptive approach for learned lossless image compression, dubbed CALLIC.
FM2S: Self-Supervised Fluorescence Microscopy Denoising With Single Noisy Image
Fluorescence microscopy has significantly advanced biological research by visualizing detailed cellular structures and biological processes.
LLV-FSR: Exploiting Large Language-Vision Prior for Face Super-resolution
Existing face super-resolution (FSR) methods have made significant advancements, but they primarily super-resolve face with limited visual information, original pixel-wise space in particular, commonly overlooking the pluralistic clues, like the higher-order depth and semantics, as well as non-visual inputs (text caption and description).
Adaptive Stereo Depth Estimation with Multi-Spectral Images Across All Lighting Conditions
Depth estimation under adverse conditions remains a significant challenge.
Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training
Learning a self-supervised Monocular Depth Estimation (MDE) model with great generalization remains significantly challenging.
Learning Lossless Compression for High Bit-Depth Volumetric Medical Image
The BD-LVIC framework skillfully divides the high bit-depth volume into two lower bit-depth segments: the Most Significant Bit-Volume (MSBV) and the Least Significant Bit-Volume (LSBV).
A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends
In this review, we delve into the AiOIR methodologies, emphasizing their architecture innovations and learning paradigm and offering a systematic review of prevalent approaches.
Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond
To address these limitations, we introduce DeFusion++, a novel framework that leverages self-supervised learning (SSL) to enhance the versatility of feature representation for different image fusion tasks.
MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields
These modular, plug-and-play strategies enhance robustness to sparse input views, accelerate rendering, and reduce memory consumption, making MCGS a practical and efficient framework for 3D Gaussian Splatting.
PVContext: Hybrid Context Model for Point Cloud Compression
Efficient storage of large-scale point cloud data has become increasingly challenging due to advancements in scanning technology.
Spatial Annealing for Efficient Few-shot Neural Rendering
Although FreeNeRF has introduced an efficient frequency annealing strategy, its operation on frequency positional encoding is incompatible with the efficient hybrid representations.
MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems.
DINO-SD: Champion Solution for ICRA 2024 RoboDepth Challenge
However, given that most of the data in the autonomous driving dataset is collected in daytime scenarios, this leads to poor depth model performance in the face of out-of-distribution(OoD) data.
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles.
Mesh Denoising Transformer
Next, we propose a dual-stream structure consisting of a Geometric Encoder branch and a Spatial Encoder branch, which jointly encode local geometry details and spatial information to fully explore multimodal information for mesh denoising.
GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression
To further expedite the network inference, we introduce context cache optimization to GroupedMixer, which caches attention activation values in cross-group token-mixers and avoids complex and duplicated computation.
The Third Monocular Depth Estimation Challenge
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC).
MaeFuse: Transferring Omni Features with Pretrained Masked Autoencoders for Infrared and Visible Image Fusion via Guided Training
Instead of being driven by downstream tasks, our model utilizes a pretrained encoder from Masked Autoencoders (MAE), which facilities the omni features extraction for low-level reconstruction and high-level vision tasks, to obtain perception friendly features with a low cost.
SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance
Neural Radiance Field (NeRF) technology has made significant strides in creating novel viewpoints.
Exploiting Self-Supervised Constraints in Image Super-Resolution
Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing.
OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition
Depression Recognition (DR) poses a considerable challenge, especially in the context of the growing concerns surrounding privacy.
SDGE: Stereo Guided Depth Estimation for 360$^\circ$ Camera Sets
We suggest building virtual pinhole cameras to resolve the distortion problem of fisheye cameras and unify the processing for the two types of 360$^\circ$ cameras.
Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios
Monocular depth estimation from RGB images plays a pivotal role in 3D vision.
A Comprehensive Survey on 3D Content Generation
Recent years have witnessed remarkable advances in artificial intelligence generated content(AIGC), with diverse input modalities, e. g., text, image, video, audio and 3D.
Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression
Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements.
Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning
Using the measurement, we analyze existing techniques for inverting samples and get some insightful information that inspires a novel loss function to reduce the inconsistency.
Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach
Recent progress in single-image super-resolution (SISR) has achieved remarkable performance, yet the computational costs of these methods remain a challenge for deployment on resource-constrained devices.
Ranked #35 on
Image Super-Resolution
on Manga109 - 4x upscaling
HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models
In the specific, our model is constructed based on Latent Diffusion Model (LDM) and elaborately designed to absorb content and style instance as conditions of LDM.
Virtual Immunohistochemistry Staining for Histological Images Assisted by Weakly-supervised Learning
Recently virtual staining technology has greatly promoted the advancement of histopathology.
On the Dynamics Under the Unhinged Loss and Beyond
In this paper, we introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze the closed-form dynamics while requiring as few simplifications or assumptions as possible.
SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data
This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023).
Dynamic Association Learning of Self-Attention and Convolution in Image Restoration
Thus, we propose to refine background textures with the predicted degradation prior in an association learning manner.
Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks.
Ranked #14 on
Image Super-Resolution
on Manga109 - 4x upscaling
Fully $1\times1$ Convolutional Network for Lightweight Image Super-Resolution
By incorporating a parameter-free spatial-shift operation, it equips the fully $1\times1$ convolutional network with powerful representation capability while impressive computational efficiency.
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
Backdoor Attacks Against Incremental Learners: An Empirical Evaluation Study
Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series.
Super-Resolving Face Image by Facial Parsing Information
In this paper, we build a novel parsing map guided face super-resolution network which extracts the face prior (i. e., parsing map) directly from low-resolution face image for the following utilization.
Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution
Building upon the NA module, we propose a lightweight single image super-resolution (SISR) network named TCSR.
Image Deblurring by Exploring In-depth Properties of Transformer
We demonstrate the effectiveness of transformer properties in improving the perceptual quality while not sacrificing the quantitative scores (PSNR) over the most competitive models, such as Uformer, Restormer, and NAFNet, on defocus deblurring and motion deblurring tasks.
Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection
In this paper, we improve the challenging monocular 3D object detection problem with a general semi-supervised framework.
Guided Depth Map Super-resolution: A Survey
Guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution (HR) depth map from a low-resolution (LR) observation with the help of a paired HR color image, is a longstanding and fundamental problem, it has attracted considerable attention from computer vision and image processing communities.
Spatial-Frequency Mutual Learning for Face Super-Resolution
To circumvent this problem, Fourier transform is introduced, which can capture global facial structure information and achieve image-size receptive field.
Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report
Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks.
Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation
During the iterative update, the results of depth estimation are compared across cameras and the information of overlapping areas is propagated to the whole depth maps with the help of basis formulation.
LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices
Notably, our solution named LiteDepth ranks 2nd in the MAI&AIM2022 Monocular Depth Estimation Challenge}, with a si-RMSE of 0. 311, an RMSE of 3. 79, and the inference time is 37$ms$ tested on the Raspberry Pi 4.
Learning Towards the Largest Margins
One of the main challenges for feature representation in deep learning-based classification is the design of appropriate loss functions that exhibit strong discriminative power.
Prototype-Anchored Learning for Learning with Imperfect Annotations
We verify the effectiveness of PAL on class-imbalanced learning and noise-tolerant learning by extensive experiments on synthetic and real-world datasets.
ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation
Further, we incorporate our ReSmooth framework with negative data augmentation strategies.
Towards Model Generalization for Monocular 3D Object Detection
However, caused by severe domain gaps (e. g., the field of view (FOV), pixel size, and object size among datasets), Mono3D detectors have difficulty in generalization, leading to drastic performance degradation on unseen domains.
GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting
Our proposed GLaMa can better capture different types of missing information by using more types of masks.
Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning
Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction.
Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Based on this, we develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain.
Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation
Most existing methods either take the end-to-end supervised learning based manner, where large amounts of pairs of sparse input and dense ground-truth are exploited as supervision information; or treat up-scaling of different scale factors as independent tasks, and have to build multiple networks to handle upsampling with varying factors.
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation
Recently, some methods reformulate it as a classification-regression task to boost the model performance, where continuous depth is estimated via a linear combination of predicted probability distributions and discrete bins.
Ranked #23 on
Monocular Depth Estimation
on KITTI Eigen split
(using extra training data)
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation
This paper aims to address the problem of supervised monocular depth estimation.
Ranked #23 on
Monocular Depth Estimation
on KITTI Eigen split
(using extra training data)
Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness
Robustness of deep neural networks (DNNs) to malicious perturbations is a hot topic in trustworthy AI.
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
A new type of non-invasive attacks emerged recently, which attempt to cast perturbation onto the target by optics based tools, such as laser beam and projector.
Towards End-to-End Image Compression and Analysis with Transformers
Meanwhile, we propose a feature aggregation module to fuse the compressed features with the selected intermediate features of the Transformer, and feed the aggregated features to a deconvolutional neural network for image reconstruction.
Deep Attentional Guided Image Filtering
Specifically, we propose an attentional kernel learning module to generate dual sets of filter kernels from the guidance and the target, respectively, and then adaptively combine them by modeling the pixel-wise dependency between the two images.
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
To bridge this gap, we aim to learn a spatial-aware visual representation that can describe the three-dimensional space and is more suitable and effective for these tasks.
A Practical Contrastive Learning Framework for Single-Image Super-Resolution
Contrastive learning has achieved remarkable success on various high-level tasks, but there are fewer contrastive learning-based methods proposed for low-level tasks.
Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution
Learning-based methods usually use a convolutional neural network (CNN) to learn the implicit priors of HSIs.
Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data
In this paper, we propose a novel weakly-supervised framework to train a monocular depth estimation network to generate HR depth maps with resolution-mismatched supervision, i. e., the inputs are HR color images and the ground-truth are low-resolution (LR) depth maps.
TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network
Recently, face super-resolution (FSR) methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e. g., facial parsing maps, facial landmarks) to focus on facial structure, thereby maintaining the consistency of the facial structure while restoring facial details.
From Less to More: Spectral Splitting and Aggregation Network for Hyperspectral Face Super-Resolution
By this spectral splitting and aggregation strategy (SSAS), we can divide the original hyperspectral image into multiple samples (\emph{from less to more}) to support the efficient training of the network and effectively exploit the spectral correlations among spectrum.
Learning with Noisy Labels via Sparse Regularization
In this paper, we theoretically prove that \textbf{any loss can be made robust to noisy labels} by restricting the network output to the set of permutations over a fixed vector.
Physics-Based Iterative Projection Complex Neural Network for Phase Retrieval in Lensless Microscopy Imaging
Specifically, we unfold the iterative process of the alternative projection phase retrieval into a feed-forward neural network, whose layers mimic the processing flow.
Asymmetric Loss Functions for Learning with Noisy Labels
Symmetric loss functions are confirmed to be robust to label noise.
BaMBNet: A Blur-aware Multi-branch Network for Defocus Deblurring
In particular, we estimate the blur amounts of different regions by the internal geometric constraint of the DP data, which measures the defocus disparity between the left and right views.
Ranked #7 on
Image Defocus Deblurring
on DPD (Dual-view)
Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report
While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference.
High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion
Specifically, to effectively extract and combine relevant information from LR depth and HR guidance, we propose a multi-modal attention based fusion (MMAF) strategy for hierarchical convolutional layers, including a feature enhance block to select valuable features and a feature recalibration block to unify the similarity metrics of modalities with different appearance characteristics.
Omniscient Video Super-Resolution
Most recent video super-resolution (SR) methods either adopt an iterative manner to deal with low-resolution (LR) frames from a temporally sliding window, or leverage the previously estimated SR output to help reconstruct the current frame recurrently.
Deep Learning-based Face Super-Resolution: A Survey
Second, we elaborate on the facial characteristics and popular datasets used in FSR.
Face Hallucination via Split-Attention in Split-Attention Network
However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).
Fully Unsupervised Person Re-identification viaSelective Contrastive Learning
In this work, we propose a novel selective contrastive learning framework for unsupervised feature learning.
Single Image Deraining via Scale-space Invariant Attention Neural Network
Image enhancement from degradation of rainy artifacts plays a critical role in outdoor visual computing systems.
Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery
Recently, single gray/RGB image super-resolution reconstruction task has been extensively studied and made significant progress by leveraging the advanced machine learning techniques based on deep convolutional neural networks (DCNNs).
Multi-Scale Progressive Fusion Network for Single Image Deraining
In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image rain streak removal.
Ranked #6 on
Single Image Deraining
on Test2800
Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis
However, the performance of CNN-based classification approach depends on a large amount of high-quality manually labeled training data, which are inevitably introduced noise on labels in practice, leading to model overfitting and performance degradation.
ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising
Hyperspectral image (HSI) denoising is of crucial importance for many subsequent applications, such as HSI classification and interpretation.
Ensemble Super-Resolution with A Reference Dataset
In this paper, we present a simple but effective single image SR method based on ensemble learning, which can produce a better performance than that could be obtained from any of SR methods to be ensembled (or called component super-resolvers).
Hyperspectral Image Classification in the Presence of Noisy Labels
The key idea of RLPA is to exploit knowledge (e. g., the superpixel based spectral-spatial constraints) from the observed hyperspectral images and apply it to the process of label propagation.
Context-Patch Face Hallucination Based on Thresholding Locality-constrained Representation and Reproducing Learning
To this end, this study incorporates the contextual information of image patch and proposes a powerful and efficient context-patch based face hallucination approach, namely Thresholding Locality-constrained Representation and Reproducing learning (TLcR-RL).
Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination
Most of the current face hallucination methods, whether they are shallow learning-based or deep learning-based, all try to learn a relationship model between Low-Resolution (LR) and High-Resolution (HR) spaces with the help of a training set.
SuperPCA: A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery
(1) Unlike the traditional PCA method based on a whole image, SuperPCA takes into account the diversity in different homogeneous regions, that is, different regions should have different projections.
