Wenhan Luo

CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing CVPR 2026 FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories CVPR 2026 MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding CVPR 2026 STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval CVPR 2026 UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass CVPR 2026 Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models CVPR 2026 Co^3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion ICLR 2025 MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion ICCV 2025 MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration ICCV 2025 OSV: One Step is Enough for High-Quality Image to Video Generation CVPR 2025 PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing CVPR 2025 StyleMaster: Stylize Your Video with Artistic Generation and Translation CVPR 2025 Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling ICLR 2025 VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension ACL 2025 A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation COLING 2024 AttnZero: Efficient Attention Discovery for Vision Transformers ECCV 2024 Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search ECCV 2024 Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost ICLR 2024 Context-Aware Integration of Language and Visual References for Natural Language Tracking CVPR 2024 DetKDS: Knowledge Distillation Search for Object Detectors ICML 2024 Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models NeurIPS 2024 Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention NeurIPS 2024 OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models ECCV 2024 Prompting Future Driven Diffusion Model for Hand Motion Prediction ECCV 2024 Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation CVPR 2024 Few-Shot Object Counting With Similarity-Aware Feature Enhancement WACV 2023 F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives ICCV 2023 Homography Guided Temporal Fusion for Road Line and Marking Segmentation ICCV 2023 MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing ICCV 2023 PRIOR: Prototype Representation Joint Learning from Medical Images and Reports ICCV 2023 Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models NeurIPS 2023 Robust Single Image Reflection Removal Against Adversarial Attacks CVPR 2023 Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method AAAI 2023 Aesthetic Text Logo Synthesis via Content-Aware Layout Inferring CVPR 2022 Benchmarking Ultra-High-Definition Image Super-Resolution ICCV 2021 Towards Distraction-Robust Active Visual Tracking ICML 2021 Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding ECCV 2020 Deblurring by Realistic Blurring CVPR 2020 Fine-Grained Image-to-Image Transformation Towards Visual Recognition CVPR 2020 AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active Tracking ICLR 2019 Cousin Network Guided Sketch Recognition via Latent Attribute Warehouse AAAI 2019 Face Anti-Spoofing: Model Matters, so Does Data CVPR 2019 Learning Joint Gait Representation via Quintuplet Loss Minimization CVPR 2019 Learning to Compose Dynamic Tree Structures for Visual Contexts CVPR 2019 Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis ICCV 2019 Residual Regression With Semantic Prior for Crowd Counting CVPR 2019 Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video ACL 2019 Bi-Real Net: Enhancing the Performance of 1-bit CNNs with Improved Representational Capability and Advanced Training Algorithm ECCV 2018 End-to-end Active Object Tracking via Reinforcement Learning ICML 2018 Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks CVPR 2018 Real-Time Neural Style Transfer for Videos CVPR 2017 Bi-label Propagation for Generic Multiple Object Tracking CVPR 2014 Unified Face Analysis by Iterative Multi-Output Random Forests CVPR 2014