Fujun Luan

16

Papers

647

Total Citations

Papers (16)

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

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

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

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

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

RNG: Relightable Neural Gaussians

Gaussian Mixture Flow Matching Models

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

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

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

RayZer: A Self-supervised Large View Synthesis Model