Xiao Sun

papers

1,377

total citations

papers (26)

Neural Articulated Radiance Field

ICCV 2021arXiv

239

citations

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

ECCV 2020arXiv

214

citations

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

ECCV 2020arXiv

150

citations

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

ICCV 2021arXiv

141

citations

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

CVPR 2022arXiv

139

citations

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

ECCV 2022arXiv

citations

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training

NEURIPS 2020arXiv

citations

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

CVPR 2024arXiv

citations

MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks

CVPR 2025arXiv

citations

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

AAAI 2025arXiv

citations

CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction

ICCV 2025arXiv

citations

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning

ICCV 2023arXiv

citations

Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence

ECCV 2024arXiv

citations

Sequential Gaussian Avatars with Hierarchical Motion Context

ICCV 2025arXiv

citations

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

ECCV 2024arXiv

citations

Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars

ICCV 2025arXiv

citations

Ultra-Low Precision 4-bit Training of Deep Neural Networks

NEURIPS 2020

citations

Q-DM: An Efficient Low-bit Quantized Diffusion Model

NEURIPS 2023

citations

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement

ICML 2024

citations

Xiao Sun

papers (26)

Neural Articulated Radiance Field

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption

PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine

Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

Bringing Rolling Shutter Images Alive with Dual Reversed Distortion

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

OccMamba: Semantic Occupancy Prediction with State Space Models

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning

Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence

Sequential Gaussian Avatars with Hierarchical Motion Context

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars

Ultra-Low Precision 4-bit Training of Deep Neural Networks

Q-DM: An Efficient Low-bit Quantized Diffusion Model

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement

papers (26)

Neural Articulated Radiance Field

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption

PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine

Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

Bringing Rolling Shutter Images Alive with Dual Reversed Distortion

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

OccMamba: Semantic Occupancy Prediction with State Space Models

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning

Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence

Sequential Gaussian Avatars with Hierarchical Motion Context

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars

Ultra-Low Precision 4-bit Training of Deep Neural Networks

Q-DM: An Efficient Low-bit Quantized Diffusion Model

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement