Miaomiao Liu

papers

1,148

total citations

papers (18)

Non-Parametric Depth Distribution Modelling Based Depth Inference for Multi-View Stereo

CVPR 2022arXiv

citations

Weakly-Supervised Action Transition Learning for Stochastic Human Motion Prediction

CVPR 2022arXiv

citations

VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos

CVPR 2023arXiv

citations

LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network

CVPR 2024arXiv

citations

Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye View

ICCV 2023arXiv

citations

HashPoint: Accelerated Point Searching and Sampling for Neural Rendering

CVPR 2024arXiv

citations

Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition

ECCV 2022arXiv

citations

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

CVPR 2024arXiv

citations

Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction

NEURIPS 2025arXiv

citations

DCHM: Depth-Consistent Human Modeling for Multiview Detection

ICCV 2025arXiv

citations

K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring

CVPR 2023

citations

Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video

CVPR 2025arXiv

citations

Miaomiao Liu

papers (18)

Cost Volume Pyramid Based Depth Inference for Multi-View Stereo

History Repeats Itself: Human Motion Prediction via Motion Attention

Generating Smooth Pose Sequences for Diverse Human Motion Prediction

Single Image Optical Flow Estimation With an Event Camera

Self-Supervised Learning of Depth Inference for Multi-View Stereo

Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration

Non-Parametric Depth Distribution Modelling Based Depth Inference for Multi-View Stereo

Weakly-Supervised Action Transition Learning for Stochastic Human Motion Prediction

VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos

LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network

Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye View

HashPoint: Accelerated Point Searching and Sampling for Neural Rendering

Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction

DCHM: Depth-Consistent Human Modeling for Multiview Detection

K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring

Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video

papers (18)

Cost Volume Pyramid Based Depth Inference for Multi-View Stereo

History Repeats Itself: Human Motion Prediction via Motion Attention

Generating Smooth Pose Sequences for Diverse Human Motion Prediction

Single Image Optical Flow Estimation With an Event Camera

Self-Supervised Learning of Depth Inference for Multi-View Stereo

Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration

Non-Parametric Depth Distribution Modelling Based Depth Inference for Multi-View Stereo

Weakly-Supervised Action Transition Learning for Stochastic Human Motion Prediction

VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos

LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network

Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye View

HashPoint: Accelerated Point Searching and Sampling for Neural Rendering

Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction

DCHM: Depth-Consistent Human Modeling for Multiview Detection

K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring

Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video