Shenghua Gao

papers

1,838

total citations

papers (27)

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

ECCV 2020arXiv

351

citations

Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement

CVPR 2020arXiv

271

citations

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

CVPR 2023arXiv

188

citations

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

NEURIPS 2023arXiv

174

citations

Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

ECCV 2020arXiv

133

citations

TransRAC: Encoding Multi-Scale Temporal Correlation With Transformers for Repetitive Action Counting

CVPR 2022arXiv

citations

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

CVPR 2024arXiv

citations

Scaling Mesh Generation via Compressive Tokenization

CVPR 2025arXiv

citations

PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes

CVPR 2023arXiv

citations

LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation

ICCV 2023arXiv

citations

Layout-Guided Novel View Synthesis From a Single Indoor Panorama

CVPR 2021arXiv

citations

SVIP: Sequence VerIfication for Procedures in Videos

CVPR 2022arXiv

citations

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties

CVPR 2025arXiv

citations

Learning To Recommend Frame for Interactive Video Object Segmentation in the Wild

CVPR 2021arXiv

citations

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

ICCV 2025arXiv

citations

Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos

CVPR 2023arXiv

citations

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

ECCV 2022arXiv

citations

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline

ICLR 2025arXiv

citations

Crowd Counting With Partial Annotations in an Image

ICCV 2021

citations

P²Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

ECCV 2020

citations

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

CVPR 2020

citations

Prior Based Human Completion

CVPR 2021

citations

HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars

CVPR 2025

citations

SIRI: Spatial Relation Induced Network For Spatial Description Resolution

NEURIPS 2020arXiv

citations

Shenghua Gao

papers (27)

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding

DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers

Speech Drives Templates: Co-Speech Gesture Synthesis With Learned Templates

TransRAC: Encoding Multi-Scale Temporal Correlation With Transformers for Repetitive Action Counting

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

Scaling Mesh Generation via Compressive Tokenization

PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes

LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation

Layout-Guided Novel View Synthesis From a Single Indoor Panorama

SVIP: Sequence VerIfication for Procedures in Videos

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties

Learning To Recommend Frame for Interactive Video Object Segmentation in the Wild

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline

Crowd Counting With Partial Annotations in an Image

P²Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

Prior Based Human Completion

HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars

SIRI: Spatial Relation Induced Network For Spatial Description Resolution

papers (27)

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding

DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers

Speech Drives Templates: Co-Speech Gesture Synthesis With Learned Templates

TransRAC: Encoding Multi-Scale Temporal Correlation With Transformers for Repetitive Action Counting

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

Scaling Mesh Generation via Compressive Tokenization

PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes

LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation

Layout-Guided Novel View Synthesis From a Single Indoor Panorama

SVIP: Sequence VerIfication for Procedures in Videos

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties

Learning To Recommend Frame for Interactive Video Object Segmentation in the Wild

FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline

Crowd Counting With Partial Annotations in an Image

P²Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

Prior Based Human Completion

HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars

SIRI: Spatial Relation Induced Network For Spatial Description Resolution