Xiaogang Xu

papers

2,279

total citations

papers (26)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

CVPR 2024arXiv

1,479

citations

LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching

CVPR 2024arXiv

282

citations

Low-Light Image Enhancement via Structure Modeling and Guidance

CVPR 2023arXiv

137

citations

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

NEURIPS 2023arXiv

citations

S2WAT: Image Style Transfer via Hierarchical Vision Transformer Using Strips Window Attention

AAAI 2024arXiv

citations

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

ECCV 2022arXiv

citations

Lighting up NeRF via Unsupervised Decomposition and Enhancement

ICCV 2023arXiv

citations

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation

ICCV 2021arXiv

citations

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

ECCV 2024arXiv

citations

Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge

ICCV 2025

citations

Self-Supervised 3D Mesh Reconstruction From Single Images

CVPR 2021

citations

SNR-Aware Low-Light Image Enhancement

CVPR 2022

citations

MTFormer: Multi-task Learning via Transformer and Cross-Task Reasoning

ECCV 2022

citations

Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment

ICCV 2021

citations

UniMODE: Unified Monocular 3D Object Detection

CVPR 2024

citations

DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection

AAAI 2025

citations

Domain Adaptive Image-to-Image Translation

CVPR 2020

citations

Co-Painter: Fine-Grained Controllable Image Stylization via Implicit Decoupling and Adaptive Injection

ICCV 2025

citations

Xiaogang Xu

papers (26)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching

Low-Light Image Enhancement via Structure Modeling and Guidance

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

S2WAT: Image Style Transfer via Hierarchical Vision Transformer Using Strips Window Attention

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Lighting up NeRF via Unsupervised Decomposition and Enhancement

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation

An Incremental Unified Framework for Small Defect Inspection

Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields

TriVol: Point Cloud Rendering via Triple Volumes

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

Boosting Image Restoration via Priors from Pre-trained Models

Generative Active Learning for Long-tailed Instance Segmentation

Learning to Remove Wrinkled Transparent Film with Polarized Prior

DiffDoctor: Diagnosing Image Diffusion Models Before Treating

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge

Self-Supervised 3D Mesh Reconstruction From Single Images

SNR-Aware Low-Light Image Enhancement

MTFormer: Multi-task Learning via Transformer and Cross-Task Reasoning

Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment

UniMODE: Unified Monocular 3D Object Detection

DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection

Domain Adaptive Image-to-Image Translation

Co-Painter: Fine-Grained Controllable Image Stylization via Implicit Decoupling and Adaptive Injection

papers (26)

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching

Low-Light Image Enhancement via Structure Modeling and Guidance

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

S2WAT: Image Style Transfer via Hierarchical Vision Transformer Using Strips Window Attention

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Lighting up NeRF via Unsupervised Decomposition and Enhancement

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation

An Incremental Unified Framework for Small Defect Inspection

Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields

TriVol: Point Cloud Rendering via Triple Volumes

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

Boosting Image Restoration via Priors from Pre-trained Models

Generative Active Learning for Long-tailed Instance Segmentation

Learning to Remove Wrinkled Transparent Film with Polarized Prior

DiffDoctor: Diagnosing Image Diffusion Models Before Treating

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge

Self-Supervised 3D Mesh Reconstruction From Single Images

SNR-Aware Low-Light Image Enhancement

MTFormer: Multi-task Learning via Transformer and Cross-Task Reasoning

Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment

UniMODE: Unified Monocular 3D Object Detection

DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection

Domain Adaptive Image-to-Image Translation

Co-Painter: Fine-Grained Controllable Image Stylization via Implicit Decoupling and Adaptive Injection