Conference | Yida Wang

caption for image

Street View Synthesis with Controllable Video Diffusion Models

caption for image

Crafting World Models for Driving Scene Reconstruction via Online Restoration

caption for image

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

caption for image

Ray-adaptive Neural Surface Reconstruction

caption for image

Learning Local Displacements for Point Cloud Completion

caption for image

Shape Descriptor for Point Cloud Completion and Classification

caption for image

Multi-Branch Volumetric Semantic Completion From a Single Depth Image

caption for image

Adversarial Semantic Scene Completion from a Single Depth Image

Efficient deep learning for real object recognition based on 3D models

Self-restraint Object Recognition by Model Based CNN Learning