Zhiwen Fan

papers

1,849

total citations

papers (20)

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

CVPR 2020arXiv

872

citations

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

CVPR 2024arXiv

335

citations

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

ECCV 2022arXiv

215

citations

Unified Implicit Neural Stylization

ECCV 2022arXiv

citations

Aug-NeRF: Training Stronger Neural Radiance Fields With Triple-Level Physically-Grounded Augmentations

CVPR 2022arXiv

citations

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts

ICCV 2023arXiv

citations

STAMP: Scalable Task- And Model-agnostic Collaborative Perception

ICLR 2025arXiv

citations

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

CVPR 2024arXiv

citations

Steepest Descent Density Control for Compact 3D Gaussian Splatting

CVPR 2025arXiv

citations

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

CVPR 2025arXiv

citations

X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction

ICCV 2025

citations

CryoFastAR: Fast Cryo-EM Ab initio Reconstruction Made Easy

ICCV 2025arXiv

citations

Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction

ECCV 2022

citations

NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views

CVPR 2023

citations

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

NEURIPS 2022

citations

CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings

CVPR 2022

citations

Zhiwen Fan

papers (20)

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

Unified Implicit Neural Stylization

Aug-NeRF: Training Stronger Neural Radiance Fields With Triple-Level Physically-Grounded Augmentations

Signal Processing for Implicit Neural Representations

FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting

StegaNeRF: Embedding Invisible Information within Neural Radiance Fields

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts

STAMP: Scalable Task- And Model-agnostic Collaborative Perception

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

Steepest Descent Density Control for Compact 3D Gaussian Splatting

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction

CryoFastAR: Fast Cryo-EM Ab initio Reconstruction Made Easy

Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction

NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings

papers (20)

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

Unified Implicit Neural Stylization

Aug-NeRF: Training Stronger Neural Radiance Fields With Triple-Level Physically-Grounded Augmentations

Signal Processing for Implicit Neural Representations

FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting

StegaNeRF: Embedding Invisible Information within Neural Radiance Fields

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts

STAMP: Scalable Task- And Model-agnostic Collaborative Perception

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

Steepest Descent Density Control for Compact 3D Gaussian Splatting

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction

CryoFastAR: Fast Cryo-EM Ab initio Reconstruction Made Easy

Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction

NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings