← Authors

Sai Bi

31 papers · 2019–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (6) 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (39) πŸ”¬ Deep Specialist (12) πŸ† Keyword Champion 🀝 Dynamic Duo (24) ⚑ Prolific Year (11) πŸ—ƒοΈ Keyword Collector (101) πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (31)

Conferences

CVPR (13) ICLR (6) ECCV (5) ICCV (3) NIPS (2) ICML (1) WACV (1)

Top co-authors

Zexiang Xu (24) Kai Zhang (19) Kalyan Sunkavalli (17) Fujun Luan (17) Hao Tan (16) Zhixin Shu (6) Haian Jin (6) Ravi Ramamoorthi (6) Milos Hasan (5) Gordon Wetzstein (4)

Research topics

Models (1)

Keywords

3d reconstruction (10) neural radiance field (9) novel view synthesis (6) scene reconstruction (5) multi-view stereo (4) neural rendering (4) large reconstruction model (3) diffusion model (3) view synthesis (3) volumetric rendering (2) inverse rendering (2) synthesized datum (2) self-supervised learning (2) procedural generation (2) gaussian splatting (2) image synthesis (1) depth estimation (1) image restoration (1) point cloud (1) model distillation (1)

Papers

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias ICLR 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
RelitLRM: Generative Relightable Radiance for Large Reconstruction Models ICLR 2025
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats ICCV 2025
RayZer: A Self-supervised Large View Synthesis Model ICCV 2025
NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support WACV 2025
Gaussian Mixture Flow Matching Models ICML 2025
LRM-Zero: Training Large Reconstruction Models with Synthesized Data NIPS 2024
Neural Gaffer: Relighting Any Object via Diffusion NIPS 2024
Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling CVPR 2024
Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning CVPR 2024
Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image CVPR 2024
DATENeRF: Depth-Aware Text-based Editing of NeRFs ECCV 2024
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting ECCV 2024
Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model ICLR 2024
DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model ICLR 2024
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction ICLR 2024
LRM: Large Reconstruction Model for Single Image to 3D ICLR 2024
PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields CVPR 2023
TensoIR: Tensorial Inverse Rendering CVPR 2023
NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction CVPR 2022
Physically-Based Editing of Indoor Scene Lighting from a Single Image ECCV 2022
Point-NeRF: Point-Based Neural Radiance Fields CVPR 2022
ARF: Artistic Radiance Fields ECCV 2022
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets CVPR 2021
Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images CVPR 2020
Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images ECCV 2020
Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement ICCV 2019