Gang Zeng

19

Papers

641

Total Citations

Papers (19)

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

Efficient Part-level 3D Object Generation via Dual Volume Packing

NeurIPS 2025arXiv

TACO: Taming Diffusion for in-the-wild Video Amodal Completion

Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction

Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF

Neural Style Transfer via Meta Networks

3D Sketch-Aware Semantic Scene Completion via Semi-Supervised Structure Prior

Semi-Supervised Semantic Segmentation With Cross Pseudo Supervision

Conditional DETR for Fast Training Convergence

Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing

Point Scene Understanding via Disentangled Instance Mesh Reconstruction

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

Fast SP-GS: Reconstructing Dynamic Scenes in Minutes

HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting

Compressible-composable NeRF via Rank-residual Decomposition

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks