Zexiang Xu

40 papers · 2017–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) 🏃 Academic Marathon (8) 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (44) 🔬 Deep Specialist (18) 🤝 Dynamic Duo (24) 💎 Century Club (40) ⚡ Prolific Year (10) 🗃️ Keyword Collector (121) 🔥 Unstoppable (6) 📈 Trend Setter

Conferences

CVPR (16) ECCV (7) ICLR (6) NIPS (5) ICCV (4) ICML (1) WACV (1)

Top co-authors

Sai Bi (24) Kalyan Sunkavalli (16) Kai Zhang (16) Fujun Luan (14) Hao Tan (13) Hao Su (11) Ravi Ramamoorthi (9) Haian Jin (7) Milos Hasan (7) Yannick Hold-Geoffroy (4)

Research topics

Keywords

3d reconstruction (15) neural radiance field (10) neural rendering (7) view synthesis (5) novel view synthesis (5) multi-view stereo (5) scene reconstruction (4) differentiable rendering (4) diffusion model (4) large reconstruction model (3) inverse rendering (3) image generation (2) sparse representation (2) depth estimation (2) indoor scene (2) point cloud (2) text-to-3d generation (2) photorealistic rendering (2) procedural generation (2) gaussian splatting (2)

Papers

NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support WACV 2025

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors CVPR 2025

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data CVPR 2025

Turbo3D: Ultra-fast Text-to-3D Generation CVPR 2025

Generating 3D-Consistent Videos from Unposed Internet Photos CVPR 2025

DMesh++: An Efficient Differentiable Mesh for Complex Shapes ICCV 2025

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats ICCV 2025

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models ICLR 2025

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias ICLR 2025

Gaussian Mixture Flow Matching Models ICML 2025

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model ICLR 2024

Neural Gaffer: Relighting Any Object via Diffusion NIPS 2024

LRM-Zero: Training Large Reconstruction Models with Synthesized Data NIPS 2024

GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting ECCV 2024

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling CVPR 2024

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction ICLR 2024

SuperGaussian: Repurposing Video Models for 3D Super Resolution ECCV 2024

DMesh: A Differentiable Mesh Representation NIPS 2024

MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field ICLR 2024

Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model ICLR 2024

TensoIR: Tensorial Inverse Rendering CVPR 2023

Strivec: Sparse Tri-Vector Radiance Fields ICCV 2023

OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects NIPS 2023

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization NIPS 2023

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation CVPR 2023

PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes CVPR 2022

RigNeRF: Fully Controllable Neural 3D Portraits CVPR 2022

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction CVPR 2022

Point-NeRF: Point-Based Neural Radiance Fields CVPR 2022

Physically-Based Editing of Indoor Scene Lighting from a Single Image ECCV 2022

ARF: Artistic Radiance Fields ECCV 2022

TensoRF: Tensorial Radiance Fields ECCV 2022

MVSNeRF: Fast Generalizable Radiance Field Reconstruction From Multi-View Stereo ICCV 2021

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets CVPR 2021

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering CVPR 2021

Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness CVPR 2020

Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images CVPR 2020

Deep Multi Depth Panoramas for View Synthesis ECCV 2020

Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images ECCV 2020

Robust Energy Minimization for BRDF-Invariant Shape From Light Fields CVPR 2017