CVPR | Yida Wang

infinidepth

Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields (InfiniDepth)

Crafting World Models for Driving Scene Reconstruction via Online Restoration

Crafting World Models for Driving Scene Reconstruction via Online Restoration (ReconDreamer)

caption for image

Street View Synthesis with Controllable Video Diffusion Models (StreetCrafter)

World Models Are Effective Data Machines for 4D Driving Scene Representation

World Models Are Effective Data Machines for 4D Driving Scene Representation (DriveDreamer4D)

disp3d

Learning Local Displacements for Point Cloud Completion