Xun Cao

papers

1,623

total citations

papers (25)

FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction

CVPR 2020arXiv

343

citations

Audio-Driven Emotional Video Portraits

CVPR 2021arXiv

274

citations

Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems

ECCV 2020arXiv

269

citations

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

ECCV 2024arXiv

239

citations

MoFaNeRF: Morphable Facial Neural Radiance Field

ECCV 2022arXiv

108

citations

FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions

CVPR 2024arXiv

citations

Explore Spatio-Temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline

CVPR 2022arXiv

citations

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

CVPR 2024arXiv

citations

EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head

ECCV 2024arXiv

citations

MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond

CVPR 2025arXiv

citations

Aperture Diffraction for Compact Snapshot Spectral Imaging

ICCV 2023arXiv

citations

A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields

AAAI 2024

citations

Mitigating Ambiguities in 3D Classification with Gaussian Splatting

CVPR 2025arXiv

citations

WIPES: Wavelet-based Visual Primitives

ICCV 2025arXiv

citations

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

ICCV 2025arXiv

citations

Efficient Snapshot Spectral Imaging: Calibration-Free Parallel Structure with Aperture Diffraction Fusion

ECCV 2024

citations

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

ICCV 2025arXiv

citations

Batch Normalization Alleviates the Spectral Bias in Coordinate Networks

CVPR 2024

citations

Xun Cao

papers (25)

FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction

Audio-Driven Emotional Video Portraits

Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

MoFaNeRF: Morphable Facial Neural Radiance Field

FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions

Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion

DINER: Disorder-Invariant Implicit Neural Representation

High-Fidelity 3D Face Generation From Natural Language Descriptions

IDOL: Instant Photorealistic 3D Human Creation from a Single Image

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Matrix3D: Large Photogrammetry Model All-in-One

FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video

Explore Spatio-Temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head

MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond

Aperture Diffraction for Compact Snapshot Spectral Imaging

A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields

Mitigating Ambiguities in 3D Classification with Gaussian Splatting

WIPES: Wavelet-based Visual Primitives

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

Efficient Snapshot Spectral Imaging: Calibration-Free Parallel Structure with Aperture Diffraction Fusion

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

Batch Normalization Alleviates the Spectral Bias in Coordinate Networks

papers (25)

FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction

Audio-Driven Emotional Video Portraits

Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

MoFaNeRF: Morphable Facial Neural Radiance Field

FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions

Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion

DINER: Disorder-Invariant Implicit Neural Representation

High-Fidelity 3D Face Generation From Natural Language Descriptions

IDOL: Instant Photorealistic 3D Human Creation from a Single Image

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Matrix3D: Large Photogrammetry Model All-in-One

FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video

Explore Spatio-Temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head

MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond

Aperture Diffraction for Compact Snapshot Spectral Imaging

A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields

Mitigating Ambiguities in 3D Classification with Gaussian Splatting

WIPES: Wavelet-based Visual Primitives

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

Efficient Snapshot Spectral Imaging: Calibration-Free Parallel Structure with Aperture Diffraction Fusion

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

Batch Normalization Alleviates the Spectral Bias in Coordinate Networks