Wei Yin

papers

1,681

total citations

papers (19)

Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

ICCV 2023arXiv

327

citations

Learning To Recover 3D Scene Shape From a Single Image

CVPR 2021arXiv

299

citations

GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

ECCV 2024arXiv

230

citations

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

CVPR 2025arXiv

citations

Learning To Fuse Monocular and Multi-View Cues for Multi-Frame Depth Estimation in Dynamic Scenes

CVPR 2023arXiv

citations

Generic Perceptual Loss for Modeling Structured Output Dependencies

CVPR 2021arXiv

citations

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving

CVPR 2024arXiv

citations

Controllable Shadow Generation Using Pixel Height Maps

ECCV 2022arXiv

citations

Epona: Autoregressive Diffusion World Model for Autonomous Driving

ICCV 2025arXiv

citations

UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving

ICLR 2024arXiv

citations

PointInst3D: Segmenting 3D Instances by Points

ECCV 2022arXiv

citations

PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion

CVPR 2024arXiv

citations

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

ICCV 2023arXiv

citations

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

ICCV 2023arXiv

citations

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

ICCV 2025arXiv

citations

Wei Yin

papers (19)

Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

Learning To Recover 3D Scene Shape From a Single Image

GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

GaussianPro: 3D Gaussian Splatting with Progressive Propagation

Retrieval Augmented Classification for Long-Tail Visual Recognition

GIM: Learning Generalizable Image Matcher From Internet Videos

Hierarchical Normalization for Robust Monocular Depth Estimation

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

Learning To Fuse Monocular and Multi-View Cues for Multi-Frame Depth Estimation in Dynamic Scenes

Generic Perceptual Loss for Modeling Structured Output Dependencies

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving

Controllable Shadow Generation Using Pixel Height Maps

Epona: Autoregressive Diffusion World Model for Autonomous Driving

UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving

PointInst3D: Segmenting 3D Instances by Points

PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion

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

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

papers (19)

Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

Learning To Recover 3D Scene Shape From a Single Image

GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

GaussianPro: 3D Gaussian Splatting with Progressive Propagation

Retrieval Augmented Classification for Long-Tail Visual Recognition

GIM: Learning Generalizable Image Matcher From Internet Videos

Hierarchical Normalization for Robust Monocular Depth Estimation

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

Learning To Fuse Monocular and Multi-View Cues for Multi-Frame Depth Estimation in Dynamic Scenes

Generic Perceptual Loss for Modeling Structured Output Dependencies

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving

Controllable Shadow Generation Using Pixel Height Maps

Epona: Autoregressive Diffusion World Model for Autonomous Driving

UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving

PointInst3D: Segmenting 3D Instances by Points

PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion

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

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration