Fujun Luan

papers

1,499

total citations

papers (22)

PhySG: Inverse Rendering With Spherical Gaussians for Physics-Based Material Editing and Relighting

CVPR 2021arXiv

409

citations

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model

ICLR 2024arXiv

227

citations

ARF: Artistic Radiance Fields

ECCV 2022arXiv

168

citations

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

ICLR 2024arXiv

155

citations

IRON: Inverse Rendering by Optimizing Neural SDFs and Materials From Photometric Images

CVPR 2022arXiv

135

citations

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

ICLR 2025arXiv

citations

RandAR: Decoder-only Autoregressive Visual Generation in Random Orders

CVPR 2025arXiv

citations

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats

ICCV 2025arXiv

citations

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

ICCV 2025arXiv

citations

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling

CVPR 2024arXiv

citations

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

ICLR 2025arXiv

citations

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

CVPR 2025arXiv

citations

Gaussian Mixture Flow Matching Models

ICML 2025arXiv

citations

RNG: Relightable Neural Gaussians

CVPR 2025arXiv

citations

Turbo3D: Ultra-fast Text-to-3D Generation

CVPR 2025arXiv

citations

DATENeRF: Depth-Aware Text-based Editing of NeRFs

ECCV 2024arXiv

citations

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors

CVPR 2025arXiv

citations

Generating 3D-Consistent Videos from Unposed Internet Photos

CVPR 2025arXiv

citations

I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

CVPR 2023

citations

Fujun Luan

papers (22)

PhySG: Inverse Rendering With Spherical Gaussians for Physics-Based Material Editing and Relighting

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model

ARF: Artistic Radiance Fields

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

IRON: Inverse Rendering by Optimizing Neural SDFs and Materials From Photometric Images

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

RandAR: Decoder-only Autoregressive Visual Generation in Random Orders

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

RayZer: A Self-supervised Large View Synthesis Model

Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Gaussian Mixture Flow Matching Models

RNG: Relightable Neural Gaussians

Turbo3D: Ultra-fast Text-to-3D Generation

DATENeRF: Depth-Aware Text-based Editing of NeRFs

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors

Generating 3D-Consistent Videos from Unposed Internet Photos

I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

papers (22)

PhySG: Inverse Rendering With Spherical Gaussians for Physics-Based Material Editing and Relighting

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model

ARF: Artistic Radiance Fields

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

IRON: Inverse Rendering by Optimizing Neural SDFs and Materials From Photometric Images

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

RandAR: Decoder-only Autoregressive Visual Generation in Random Orders

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

RayZer: A Self-supervised Large View Synthesis Model

Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Gaussian Mixture Flow Matching Models

RNG: Relightable Neural Gaussians

Turbo3D: Ultra-fast Text-to-3D Generation

DATENeRF: Depth-Aware Text-based Editing of NeRFs

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors

Generating 3D-Consistent Videos from Unposed Internet Photos

I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs