Conference | Yida Wang

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

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

raneus

Ray-adaptive Neural Surface Reconstruction (RaNeuS)

disp3d

Learning Local Displacements for Point Cloud Completion

softpoolnet

Shape Descriptor for Point Cloud Completion and Classification (SoftPoolNet)

forkent

Multi-Branch Volumetric Semantic Completion From a Single Depth Image (ForkNet)

sscgan

Adversarial Semantic Scene Completion from a Single Depth Image

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

Self-restraint Object Recognition by Model Based CNN Learning