Gang Zeng

papers

4,490

total citations

papers (17)

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

NEURIPS 2023arXiv

625

citations

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

ECCV 2020arXiv

407

citations

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

ICCV 2023arXiv

204

citations

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

CVPR 2020arXiv

166

citations

Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

ICCV 2023arXiv

156

citations

Compressible-composable NeRF via Rank-residual Decomposition

NEURIPS 2022arXiv

111

citations

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

CVPR 2024arXiv

105

citations

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

ECCV 2020arXiv

citations

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

ICML 2024arXiv

citations

Point Scene Understanding via Disentangled Instance Mesh Reconstruction

ECCV 2022arXiv

citations

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

NEURIPS 2025arXiv

citations

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

ICCV 2025arXiv

citations

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

CVPR 2025arXiv

citations

Fast SP-GS: Reconstructing Dynamic Scenes in Minutes

ISMAR 2025

citations

Gang Zeng

papers (17)

Semi-Supervised Semantic Segmentation With Cross Pseudo Supervision

Conditional DETR for Fast Training Convergence

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

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

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

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

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

Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

Compressible-composable NeRF via Rank-residual Decomposition

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

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

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

Point Scene Understanding via Disentangled Instance Mesh Reconstruction

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

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

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

Fast SP-GS: Reconstructing Dynamic Scenes in Minutes

papers (17)

Semi-Supervised Semantic Segmentation With Cross Pseudo Supervision

Conditional DETR for Fast Training Convergence

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

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

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

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

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

Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

Compressible-composable NeRF via Rank-residual Decomposition

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

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

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

Point Scene Understanding via Disentangled Instance Mesh Reconstruction

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

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

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

Fast SP-GS: Reconstructing Dynamic Scenes in Minutes