Zexiang Xu

33

Papers

852

Total Citations

Papers (33)

GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting

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

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

Deep Multi Depth Panoramas for View Synthesis

SuperGaussian: Repurposing Video Models for 3D Super Resolution

Gaussian Mixture Flow Matching Models

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

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

Generating 3D-Consistent Videos from Unposed Internet Photos

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

TensoIR: Tensorial Inverse Rendering

MVSNeRF: Fast Generalizable Radiance Field Reconstruction From Multi-View Stereo

Strivec: Sparse Tri-Vector Radiance Fields

Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images

Physically-Based Editing of Indoor Scene Lighting from a Single Image

ARF: Artistic Radiance Fields

TensoRF: Tensorial Radiance Fields

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

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

Robust Energy Minimization for BRDF-Invariant Shape From Light Fields

Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness

Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes

RigNeRF: Fully Controllable Neural 3D Portraits

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

Point-NeRF: Point-Based Neural Radiance Fields

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization

OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects