Search Results for author:
Found 74 papers, 43 papers with code
Frequency-aware Feature Fusion for Dense Image Prediction
The offset generator refines large inconsistent features and thin boundaries by replacing inconsistent features with more consistent ones through resampling, while the AHPF generator enhances high-frequency detailed boundary information lost during downsampling.
FCDFusion: a Fast, Low Color Deviation Method for Fusing Visible and Infrared Image Pairs
Compared to state-of-the-art fast, color-preserving methods using HSV color space, our method provides higher contrast at only half of the computational cost.
PerlDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models
In this paper, we explore the integration of controlling information and introduce PerlDiff (Perspective-Layout Diffusion Models), a method for effective street view image generation that fully leverages perspective 3D geometric information.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Multi-Object Tracking in the Dark
We conducted a comprehensive analysis of our LMOT dataset and proposed LTrack.
Aligning LLMs for FL-free Program Repair
Our core insight is that LLM's APR capability can be greatly improved by simply aligning the output to their training objective and allowing them to refine the whole program without first performing fault localization.
Transformer based Pluralistic Image Completion with Reduced Information Loss
The indices of quantized pixels are used as tokens for the inputs and prediction targets of the transformer.
Binarized Low-light Raw Video Enhancement
For the second issue, we present a distribution-aware binary convolution, which captures the distribution characteristics of real-valued input and incorporates them into plain binary convolutions to alleviate the degradation in performance.
Infrared Small Target Detection with Scale and Location Sensitivity
In this paper, we focus on boosting detection performance with a more effective loss but a simpler model structure.
LLMs Instruct LLMs:An Extraction and Editing Method
The interest in updating Large Language Models (LLMs) without retraining from scratch is substantial, yet it comes with some challenges. This is especially true for situations demanding complex reasoning with limited samples, a scenario we refer to as the Paucity-Constrained Complex Reasoning Adaptation for LLMs (PCRA-LLM). Traditional methods like Low-Rank Adaptation (LoRA) and Retrieval-Augmented Generation (RAG) are inadequate for this critical issue, particularly evident in our exploration of a specific medical context that epitomize the PCRA-LLM's distinct needs. To address the issue, we propose a Sequential Fusion method to incorporate knowledge from complex context into LLMs.
Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations
This is particularly true for medical image segmentation (MIS) datasets, where the processes of collection and fine-grained annotation are time-intensive and laborious.
When Semantic Segmentation Meets Frequency Aliasing
While positively correlated with the proposed aliasing score, three types of hard pixels exhibit different patterns.
Frequency-Adaptive Dilated Convolution for Semantic Segmentation
Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision.
Degradation Modeling and Prognostic Analysis Under Unknown Failure Modes
Then, using these degradation trajectories, we develop a time series-based clustering method to identify the training units' failure modes.
Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing
Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks.
Masked Conditional Diffusion Model for Enhancing Deepfake Detection
this paper present we put a new insight into diffusion model-based data augmentation, and propose a Masked Conditional Diffusion Model (MCDM) for enhancing deepfake detection.
Comparative Study on the Performance of Categorical Variable Encoders in Classification and Regression Tasks
This study broadly classifies machine learning models into three categories: 1) ATI models that implicitly perform affine transformations on inputs, such as multi-layer perceptron neural network; 2) Tree-based models that are based on decision trees, such as random forest; and 3) the rest, such as kNN.
CascadeV-Det: Cascade Point Voting for 3D Object Detection
Additionally, since model training can suffer from a lack of proposal points with high centerness, we have developed the CPA module to narrow down the positive assignment threshold with cascade stages.
Learning Visual Prompt for Gait Recognition
However gait recognition in real-world scenarios is challenging due to the limitations of capturing comprehensive cross-viewing and cross-clothing data.
Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion
Nonetheless, the performance of these methods is often constrained by the domain gap and looser constraints.
Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging
Snapshot compressive spectral imaging reconstruction aims to reconstruct three-dimensional spatial-spectral images from a single-shot two-dimensional compressed measurement.
Siamese-DETR for Generic Multi-Object Tracking
Recently, Open-Vocabulary MOT (OVMOT) and Generic MOT (GMOT) are proposed to track interested objects beyond pre-defined categories with the given text prompt and template image.
CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition
Deepfake technology poses a significant threat to security and social trust.
MPI-Flow: Learning Realistic Optical Flow with Multiplane Images
The accuracy of learning-based optical flow estimation models heavily relies on the realism of the training datasets.
RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image
Unlike existing methods, the core idea of this work is to incorporate more informative Raw sensor data to generate HDR images, aiming to recover scene information in hard regions (the darkest and brightest areas of an HDR scene).
Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction
3) stage interaction ignoring the differences in features at different stages.
Recurrent Self-Supervised Video Denoising with Denser Receptive Field
However, under their blind spot constraints, previous self-supervised video denoising methods suffer from significant information loss and texture destruction in either the whole reference frame or neighbor frames, due to their inadequate consideration of the receptive field.
Denoising Diffusion Semantic Segmentation with Mask Prior Modeling
In this paper, we propose to ameliorate the semantic segmentation quality of existing discriminative approaches with a mask prior modeled by a recently-developed denoising diffusion generative model.
Instance Segmentation in the Dark
Existing instance segmentation techniques are primarily tailored for high-visibility inputs, but their performance significantly deteriorates in extremely low-light environments.
Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising
In this paper, we address these issues by proposing a spectral enhanced rectangle Transformer, driving it to explore the non-local spatial similarity and global spectral low-rank property of HSIs.
LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising
Despite the significant results on synthetic noise under simplified assumptions, most self-supervised denoising methods fail under real noise due to the strong spatial noise correlation, including the advanced self-supervised blind-spot networks (BSNs).
Hybrid Spectral Denoising Transformer with Guided Attention
Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the global and local spatial-spectral correlations while maintaining efficiency and flexibility.
HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks
Hypergraph neural networks (HGNN) have shown superior performance in various deep learning tasks, leveraging the high-order representation ability to formulate complex correlations among data by connecting two or more nodes through hyperedge modeling.
Hyperspectral Image Super Resolution with Real Unaligned RGB Guidance
The features of RGB reference images are then processed by a multi-stage alignment module to explicitly align the features of RGB reference with the LR HSI.
Mixed Attention Network for Hyperspectral Image Denoising
However, existing methods show limitations in exploring the spectral correlations across different bands and feature interactions within each band.
Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising
However, the unavailable noise prior and inefficient feature extraction take these methods away from high practicality and precision.
Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference
We propose a Semantic Alignment and Affinity Inference framework (SAAI), which aims to align latent semantic part features with the learnable prototypes and improve inference with affinity information.
Learning Rain Location Prior for Nighttime Deraining
This learned prior contains location information of rain streaks and, when injected into deraining models, can significantly improve their performance.
Fine-grained Unsupervised Domain Adaptation for Gait Recognition
Gait recognition has emerged as a promising technique for the long-range retrieval of pedestrians, providing numerous advantages such as accurate identification in challenging conditions and non-intrusiveness, making it highly desirable for improving public safety and security.
Dynamic Aggregated Network for Gait Recognition
Specifically, we create a dynamic attention mechanism between the features of neighboring pixels that not only adaptively focuses on key regions but also generates more expressive local motion patterns.
Improved Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
Hyperspectral image is unique and useful for its abundant spectral bands, but it subsequently requires extra elaborated treatments of the spatial-spectral correlation as well as the global correlation along the spectrum for building a robust and powerful HSI restoration algorithm.
Spatial-Spectral Transformer for Hyperspectral Image Denoising
Hyperspectral image (HSI) denoising is a crucial preprocessing procedure for the subsequent HSI applications.
GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removal
In this paper, we propose GTAV-NightRain dataset, which is a large-scale synthetic night-time rain streak removal dataset.
Deep Plug-and-Play Prior for Hyperspectral Image Restoration
Deep-learning-based hyperspectral image (HSI) restoration methods have gained great popularity for their remarkable performance but often demand expensive network retraining whenever the specifics of task changes.
ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling
Existing state-of-the-art novel view synthesis methods rely on either fairly accurate 3D geometry estimation or sampling of the entire space for neural volumetric rendering, which limit the overall efficiency.
Estimating Fine-Grained Noise Model via Contrastive Learning
In this work, we combine both noise modeling and estimation, and propose an innovative noise model estimation and noise synthesis pipeline for realistic noisy image generation.
End-to-End Video Text Spotting with Transformer
Recent video text spotting methods usually require the three-staged pipeline, i. e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results.
Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading
In this proposed scheme, we design a normalized modality contrastive loss (NMC-loss), which could promote to disentangle multi-modality complementary representation of FFPE and frozen sections from the same patient.
Physics-based Noise Modeling for Extreme Low-light Photography
Enhancing the visibility in extreme low-light environments is a challenging task.
Ranked #4 on
Image Denoising
on SID SonyA7S2 x100
Dynamic Proximal Unrolling Network for Compressive Imaging
In this paper, a dynamic proximal unrolling network (dubbed DPUNet) was proposed, which can handle a variety of measurement matrices via one single model without retraining.
Learning To Reconstruct High Speed and High Dynamic Range Videos From Events
Event cameras are novel sensors that capture the dynamics of a scene asynchronously.
Learning Temporal Consistency for Low Light Video Enhancement From Single Images
Based on this idea, we propose our method which can infer motion prior for single image low light video enhancement and enforce temporal consistency.
LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation
By combining the local transformer with the multiscale structure, the network is able to capture long-short range correspondences efficiently and accurately.
Disentangled Face Attribute Editing via Instance-Aware Latent Space Search
We further propose a Disentanglement-Transformation (DT) metric to quantify the attribute transformation and disentanglement efficacy and find the optimal control factor between attribute-level and instance-specific directions based on it.
Probing quasi-long-range ordering by magnetostriction in monolayer CoPS3
Mermin-Wagner-Coleman theorem predicts no long-range magnetic order at finite temperature in the two-dimensional (2D) isotropic systems, but a quasi-long-range order with a divergent correlation length at the Kosterlitz-Thouless (KT) transition for planar magnets.
Mesoscale and Nanoscale Physics
Hyperspectral Image Denoising With Realistic Data
On the other hand, we propose an accurate HSI noise model which matches the distribution of real data well and can be employed to synthesize realistic dataset.
Weakly-supervised Semantic Segmentation in Cityscape via Hyperspectral Image
It is based on the idea that high-resolution HSIs in city scenes contain rich spectral information, which can be easily associated to semantics without manual labeling.
GPS-Net: Graph-based Photometric Stereo Network
For all-pixel operation, we propose the Normal Regression Network to make efficient use of the intra-image spatial information for predicting a surface normal map with rich details.
Cross-MPI: Cross-scale Stereo for Image Super-Resolution using Multiplane Images
Various combinations of cameras enrich computational photography, among which reference-based superresolution (RefSR) plays a critical role in multiscale imaging systems.
TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
In this work, we present a class of tuning-free PnP proximal algorithms that can determine parameters such as denoising strength, termination time, and other optimization-specific parameters automatically.
Partial FC: Training 10 Million Identities on a Single Machine
The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks.
Ranked #2 on
Face Identification
on MegaFace
EasyQuant: Post-training Quantization via Scale Optimization
The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications.
A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising
Lacking rich and realistic data, learned single image denoising algorithms generalize poorly to real raw images that do not resemble the data used for training.
Ranked #5 on
Image Denoising
on ELD SonyA7S2 x200
3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
In this paper, we propose an alternating directional 3D quasi-recurrent neural network for hyperspectral image (HSI) denoising, which can effectively embed the domain knowledge -- structural spatio-spectral correlation and global correlation along spectrum.
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
Moreover, we discuss the practical considerations of the plugged denoisers, which together with our learned policy yield state-of-the-art results.
Hyperspectral City V1.0 Dataset and Benchmark
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.
Hyperspectral Image Super-Resolution With Optimized RGB Guidance
To overcome the limitations of existing hyperspectral cameras on spatial/temporal resolution, fusing a low resolution hyperspectral image (HSI) with a high resolution RGB (or multispectral) image into a high resolution HSI has been prevalent.
Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements
Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems.
Ranked #2 on
Reflection Removal
on SIR^2(Objects)
Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery
Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS).
Image Restoration from Patch-based Compressed Sensing Measurement
A series of methods have been proposed to reconstruct an image from compressively sensed random measurement, but most of them have high time complexity and are inappropriate for patch-based compressed sensing capture, because of their serious blocky artifacts in the restoration results.
Exploiting Spectral-Spatial Correlation for Coded Hyperspectral Image Restoration
In this paper, we propose an effective method for coded hyperspectral image restoration, which exploits extensive structure sparsity in the hyperspectral image.
Separating Fluorescent and Reflective Components by Using a Single Hyperspectral Image
This paper introduces a novel method to separate fluorescent and reflective components in the spectral domain.
Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising
Hyperspectral imaging is beneficial in a diverse range of applications from diagnostic medicine, to agriculture, to surveillance to name a few.
Reflectance and Fluorescent Spectra Recovery based on Fluorescent Chromaticity Invariance under Varying Illumination
We then show that given the spectral reflectance and fluorescent chromaticity, the fluorescence absorption and emission spectra can also be estimated.
