Sai Bi

OpenReview

papers

3,185

total citations

papers (26)

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

ICLR 2024arXiv

155

citations

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

CVPR 2022arXiv

143

citations

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

ECCV 2020arXiv

140

citations

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

CVPR 2020arXiv

102

citations

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

ICLR 2025arXiv

citations

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

ECCV 2022arXiv

citations

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

ICCV 2025arXiv

citations

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

CVPR 2023arXiv

citations

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

CVPR 2024arXiv

citations

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

CVPR 2024arXiv

citations

RayZer: A Self-supervised Large View Synthesis Model

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

Gaussian Mixture Flow Matching Models

ICML 2025arXiv

citations

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

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

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

CVPR 2021

citations

Sai Bi

papers (26)

LRM: Large Reconstruction Model for Single Image to 3D

Point-NeRF: Point-Based Neural Radiance Fields

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

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

ARF: Artistic Radiance Fields

TensoIR: Tensorial Inverse Rendering

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

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

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

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

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

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

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

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

RayZer: A Self-supervised Large View Synthesis Model

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

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Gaussian Mixture Flow Matching Models

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

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

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

papers (26)

LRM: Large Reconstruction Model for Single Image to 3D

Point-NeRF: Point-Based Neural Radiance Fields

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

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

ARF: Artistic Radiance Fields

TensoIR: Tensorial Inverse Rendering

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

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

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

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

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

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

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

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

RayZer: A Self-supervised Large View Synthesis Model

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

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Gaussian Mixture Flow Matching Models

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

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

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets