Wangmeng Zuo

110

Papers

248

Total Citations

Papers (110)

GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection

Improving Image Restoration through Removing Degradations in Textual Representations

PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis

MC^2: Multi-concept Guidance for Customized Multi-concept Generation

MV-VTON: Multi-View Virtual Try-On with Diffusion Models

S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting

Self-Supervised Video Desmoking for Laparoscopic Surgery

FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

ACE: Anti-Editing Concept Erasure in Text-to-Image Models

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving

MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM

NeurIPS 2025arXiv

Triad: Empowering LMM-based Anomaly Detection with Expert-guided Region-of-Interest Tokenizer and Manufacturing Process

Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization

Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection

Deep Structured Scene Parsing by Learning With Image Descriptions

A Probabilistic Collaborative Representation Based Approach for Pattern Classification

The Solution Path Algorithm for Identity-Aware Multi-Object Tracking

RAID-G: Robust Estimation of Approximate Infinite Dimensional Gaussian With Application to Material Recognition

Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation

Learning Dynamic Guidance for Depth Image Enhancement

Learning Deep CNN Denoiser Prior for Image Restoration

Multi-Scale Location-Aware Kernel Representation for Object Detection

Learning Convolutional Networks for Content-Weighted Image Compression

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category Shift

Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking

Generative Adversarial Learning Towards Fast Weakly Supervised Detection

VITAL: VIsual Tracking via Adversarial Learning

Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

Blind Super-Resolution With Iterative Kernel Correction

Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels

Toward Convolutional Blind Denoising of Real Photographs

STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

Progressive Image Deraining Networks: A Better and Simpler Baseline

Deep Global Generalized Gaussian Networks

DAVANet: Stereo Deblurring With View Aggregation

Neural Blind Deconvolution Using Deep Priors

Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion

Towards Photo-Realistic Virtual Try-On by Adaptively Generating-Preserving Image Content

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective

VirFace: Enhancing Face Recognition via Unlabeled Shallow Data

Learning Semantic Person Image Generation by Region-Adaptive Normalization

Learning Scalable lY=-Constrained Near-Lossless Image Compression via Joint Lossy Image and Residual Compression

Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment

Retrieval-Based Spatially Adaptive Normalization for Semantic Image Synthesis

Localization Distillation for Dense Object Detection

Semantic-Shape Adaptive Feature Modulation for Semantic Image Synthesis

NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN

Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography

Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time

Learning Generative Structure Prior for Blind Text Image Super-Resolution

Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis

Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising

Learning Federated Visual Prompt in Null Space for MRI Reconstruction

Texts as Images in Prompt Tuning for Multi-Label Image Recognition

Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising

Convolutional Sparse Coding for Image Super-Resolution

Higher-Order Integration of Hierarchical Convolutional Activations for Fine-Grained Visual Categorization

Joint Convolutional Analysis and Synthesis Sparse Representation for Single Image Layer Separation

Is Second-Order Information Helpful for Large-Scale Visual Recognition?

Perspective-Guided Convolution Networks for Crowd Counting

Spatio-Temporal Filter Adaptive Network for Video Deblurring

Image Inpainting With Learnable Bidirectional Attention Maps

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting

Learning RAW-to-sRGB Mappings With Inaccurately Aligned Supervision

Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

Bringing Events Into Video Deblurring With Non-Consecutively Blurry Frames

Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive

MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces

CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-Training

Towards Instance-adaptive Inference for Federated Learning

Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning

Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition

ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation

Unpaired Learning of Deep Image Denoising

Component Divide-and-Conquer for Real-World Image Super-Resolution

Blind Face Restoration via Deep Multi-scale Component Dictionaries

Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision

Adversarial Contrastive Learning via Asymmetric InfoNCE

From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution

Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-Ahead Forward Ones

Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations

Self-Promoted Supervision for Few-Shot Transformer

W2N: Switching from Weak Supervision to Noisy Supervision for Object Detection

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

Generative Inbetweening through Frame-wise Conditions-Driven Video Generation

CASP: Consistency-aware Audio-induced Saliency Prediction Model for Omnidirectional Video

ReMP-AD: Retrieval-enhanced Multi-modal Prompt Fusion for Few-Shot Industrial Visual Anomaly Detection

QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation

VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering

DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors

Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising

VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models

Learning Real-World Image De-weathering with Imperfect Supervision

3752 Decoupled Textual Embeddings for Customized Image Generation

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

Discriminative Learning of Iteration-Wise Priors for Blind Deconvolution

SOLD: Sub-Optimal Low-rank Decomposition for Efficient Video Segmentation

Joint Learning of Single-Image and Cross-Image Representations for Person Re-Identification

Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation

Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks

Cross-Scale Internal Graph Neural Network for Image Super-Resolution

Self-Supervised Image Restoration with Blurry and Noisy Pairs

Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks

Improving Adversarial Transferability via Intermediate-level Perturbation Decay

Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly