Feng Zhao

42

Papers

62

Total Citations

Papers (42)

Stream Query Denoising for Vectorized HD-Map Construction

Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing

Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes

Navigating Image Restoration with VAR’s Distribution Alignment Prior

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models

Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution

FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection

Graph Reasoning Transformers for Knowledge-Aware Question Answering

Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance

Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion

Discrete Latent Perspective Learning for Segmentation and Detection

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Mutual Information-Driven Pan-Sharpening

Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification

Bijective Mapping Network for Shadow Removal

Exposure Normalization and Compensation for Multiple-Exposure Correction

Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark

Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View

Learning Sample Relationship for Exposure Correction

Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery

Ingredient-Oriented Multi-Degradation Learning for Image Restoration

Exploring Temporal Frequency Spectrum in Deep Video Deblurring

Learning from Noisy Data for Semi-Supervised 3D Object Detection

Empowering Low-Light Image Enhancer through Customized Learnable Priors

FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models

DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection

Spatial-Frequency Domain Information Integration for Pan-Sharpening

Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction

Frequency and Spatial Dual Guidance for Image Dehazing

VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping

FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component Analysis

SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling

Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network

Deep Fourier Up-Sampling

Roadblocks for Temporarily Disabling Shortcuts and Learning New Knowledge

FouriDown: Factoring Down-Sampling into Shuffling and Superposing

Transition-constant Normalization for Image Enhancement

Deep Fractional Fourier Transform