Jingwei Huang

22

Papers

157

Total Citations

Papers (22)

SAI3D: Segment Any Instance in 3D Scenes

Deformation-Aware 3D Model Embedding and Retrieval

Epona: Autoregressive Diffusion World Model for Autonomous Driving

CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoor Object Detection from Multi-view Images

MaRI: Material Retrieval Integration across Domains

NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis

SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

FrameNet: Learning Local Canonical Frames of 3D Surfaces From a Single RGB Image

PrimitiveNet: Primitive Instance Segmentation With Local Primitive Embedding Under Adversarial Metric

EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo

Regularized Primitive Graph Learning for Unified Vector Mapping

LeaF: Learning Frames for 4D Point Cloud Sequence Understanding

Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding

DeepLM: Large-Scale Nonlinear Least Squares on Deep Learning Frameworks Using Stochastic Domain Decomposition

Unleashing Vecset Diffusion Model for Fast Shape Generation

Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes

Adversarial Texture Optimization From RGB-D Scans

Local Implicit Grid Representations for 3D Scenes

Automatic Thumbnail Generation Based on Visual Representativeness and Foreground Recognizability

NeurVPS: Neural Vanishing Point Scanning via Conic Convolution

ShapeFlow: Learnable Deformation Flows Among 3D Shapes