Wenhan Luo

papers

1,006

total citations

papers (22)

Deblurring by Realistic Blurring

CVPR 2020arXiv

440

citations

MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

ICCV 2023arXiv

193

citations

PRIOR: Prototype Representation Joint Learning from Medical Images and Reports

ICCV 2023arXiv

citations

Context-Aware Integration of Language and Visual References for Natural Language Tracking

CVPR 2024arXiv

citations

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation

CVPR 2024arXiv

citations

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

ECCV 2024

citations

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

ICCV 2025arXiv

citations

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

CVPR 2025arXiv

citations

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

ICCV 2023arXiv

citations

F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives

ICCV 2023

citations

Benchmarking Ultra-High-Definition Image Super-Resolution

ICCV 2021

citations

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

ECCV 2020

citations

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

NEURIPS 2023

citations

DetKDS: Knowledge Distillation Search for Object Detectors

ICML 2024

citations

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

ICCV 2025

citations

Robust Single Image Reflection Removal Against Adversarial Attacks

CVPR 2023

citations

Wenhan Luo

papers (22)

Deblurring by Realistic Blurring

MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

PRIOR: Prototype Representation Joint Learning from Medical Images and Reports

Context-Aware Integration of Language and Visual References for Natural Language Tracking

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

StyleMaster: Stylize Your Video with Artistic Generation and Translation

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

Aesthetic Text Logo Synthesis via Content-Aware Layout Inferring

Fine-Grained Image-to-Image Transformation Towards Visual Recognition

OSV: One Step is Enough for High-Quality Image to Video Generation

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives

Benchmarking Ultra-High-Definition Image Super-Resolution

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

DetKDS: Knowledge Distillation Search for Object Detectors

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

Robust Single Image Reflection Removal Against Adversarial Attacks

papers (22)

Deblurring by Realistic Blurring

MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

PRIOR: Prototype Representation Joint Learning from Medical Images and Reports

Context-Aware Integration of Language and Visual References for Natural Language Tracking

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

StyleMaster: Stylize Your Video with Artistic Generation and Translation

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

Aesthetic Text Logo Synthesis via Content-Aware Layout Inferring

Fine-Grained Image-to-Image Transformation Towards Visual Recognition

OSV: One Step is Enough for High-Quality Image to Video Generation

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives

Benchmarking Ultra-High-Definition Image Super-Resolution

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

DetKDS: Knowledge Distillation Search for Object Detectors

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

Robust Single Image Reflection Removal Against Adversarial Attacks