Haoqiang Fan

papers

2,358

total citations

papers (24)

PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation

CVPR 2020arXiv

547

citations

Practical Stereo Matching via Cascaded Recurrent Network With Adaptive Correlation

CVPR 2022arXiv

343

citations

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

CVPR 2021arXiv

315

citations

NBNet: Noise Basis Learning for Image Denoising With Subspace Projection

CVPR 2021arXiv

216

citations

Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization

CVPR 2023arXiv

201

citations

Motion Basis Learning for Unsupervised Deep Homography Estimation With Subspace Projection

ICCV 2021arXiv

citations

FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation

AAAI 2025arXiv

citations

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

ICCV 2025arXiv

citations

GAFlow: Incorporating Gaussian Attention into Optical Flow

ICCV 2023arXiv

citations

RealFlow: EM-Based Realistic Optical Flow Dataset Generation from Videos

ECCV 2022arXiv

citations

Efficient One Pass Self-Distillation with Zipf’s Label Smoothing

ECCV 2022arXiv

citations

MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion

ICCV 2023arXiv

citations

Practical Wide-Angle Portraits Correction With Deep Structured Models

CVPR 2021arXiv

citations

D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution

ECCV 2022arXiv

citations

Supervised Homography Learning with Realistic Dataset Generation

ICCV 2023arXiv

citations

Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion

ECCV 2024arXiv

citations

Diff-Shadow: Global-guided Diffusion Model for Shadow Removal

AAAI 2025arXiv

citations

MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer

AAAI 2025

citations

Realistic Noise Synthesis with Diffusion Models

AAAI 2025arXiv

citations

FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models

CVPR 2024

citations

Haoqiang Fan

papers (24)

PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation

Practical Stereo Matching via Cascaded Recurrent Network With Adaptive Correlation

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

NBNet: Noise Basis Learning for Image Denoising With Subspace Projection

Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization

Deep Constrained Least Squares for Blind Image Super-Resolution

FS6D: Few-Shot 6D Pose Estimation of Novel Objects

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning

Explaining Deepfake Detection by Analysing Image Matching

Motion Basis Learning for Unsupervised Deep Homography Estimation With Subspace Projection

FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

GAFlow: Incorporating Gaussian Attention into Optical Flow

RealFlow: EM-Based Realistic Optical Flow Dataset Generation from Videos

Efficient One Pass Self-Distillation with Zipf’s Label Smoothing

MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion

Practical Wide-Angle Portraits Correction With Deep Structured Models

D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution

Supervised Homography Learning with Realistic Dataset Generation

Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion

Diff-Shadow: Global-guided Diffusion Model for Shadow Removal

MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer

Realistic Noise Synthesis with Diffusion Models

FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models

papers (24)

PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation

Practical Stereo Matching via Cascaded Recurrent Network With Adaptive Correlation

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

NBNet: Noise Basis Learning for Image Denoising With Subspace Projection

Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization

Deep Constrained Least Squares for Blind Image Super-Resolution

FS6D: Few-Shot 6D Pose Estimation of Novel Objects

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning

Explaining Deepfake Detection by Analysing Image Matching

Motion Basis Learning for Unsupervised Deep Homography Estimation With Subspace Projection

FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

GAFlow: Incorporating Gaussian Attention into Optical Flow

RealFlow: EM-Based Realistic Optical Flow Dataset Generation from Videos

Efficient One Pass Self-Distillation with Zipf’s Label Smoothing

MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion

Practical Wide-Angle Portraits Correction With Deep Structured Models

D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution

Supervised Homography Learning with Realistic Dataset Generation

Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion

Diff-Shadow: Global-guided Diffusion Model for Shadow Removal

MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer

Realistic Noise Synthesis with Diffusion Models

FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models