Jiahui Huang

13

Papers

265

Total Citations

Papers (13)

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

DI-Fusion: Online Implicit 3D Reconstruction With Deep Priors

Neural Kernel Surface Reconstruction

ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation

DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion

Duality Diagram Similarity: a generic framework for initialization selection in task transfer learning

Layered Controllable Video Generation

CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene

Dynamic 3D Scene Analysis by Point Cloud Accumulation

InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models