Bihan Wen

papers

677

total citations

papers (24)

SinSR: Diffusion-Based Image Super-Resolution in a Single Step

CVPR 2024arXiv

226

citations

ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal

CVPR 2023arXiv

150

citations

ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

ICCV 2023arXiv

citations

Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation

ECCV 2024arXiv

citations

SegPoint: Segment Any Point Cloud via Large Language Model

ECCV 2024arXiv

citations

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

NEURIPS 2025arXiv

citations

WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes

NEURIPS 2023arXiv

citations

Raw Image Reconstruction With Learned Compact Metadata

CVPR 2023arXiv

citations

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

CVPR 2024arXiv

citations

GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding

ICCV 2025arXiv

citations

SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation

ICCV 2025arXiv

citations

Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual

CVPR 2025arXiv

citations

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

ICCV 2025arXiv

citations

Frequency Guidance Matters in Few-Shot Learning

ICCV 2023

citations

CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection

CVPR 2024

citations

sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model

CVPR 2023

citations

Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach

ICML 2024

citations

DVS-Voltmeter: Stochastic Process-Based Event Simulator for Dynamic Vision Sensors

ECCV 2022

citations

Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal

ICCV 2023

citations

Bihan Wen

papers (24)

SinSR: Diffusion-Based Image Super-Resolution in a Single Step

ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal

ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation

SegPoint: Segment Any Point Cloud via Large Language Model

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes

Raw Image Reconstruction With Learned Compact Metadata

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation

PIP: Physical Interaction Prediction via Mental Simulation with Span Selection

Training-Free Text-Guided Image Editing with Visual Autoregressive Model

SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal

Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning

GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding

SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation

Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

Frequency Guidance Matters in Few-Shot Learning

CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection

sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model

Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach

DVS-Voltmeter: Stochastic Process-Based Event Simulator for Dynamic Vision Sensors

Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal

papers (24)

SinSR: Diffusion-Based Image Super-Resolution in a Single Step

ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal

ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation

SegPoint: Segment Any Point Cloud via Large Language Model

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes

Raw Image Reconstruction With Learned Compact Metadata

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation

PIP: Physical Interaction Prediction via Mental Simulation with Span Selection

Training-Free Text-Guided Image Editing with Visual Autoregressive Model

SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal

Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning

GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding

SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation

Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

Frequency Guidance Matters in Few-Shot Learning

CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection

sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model

Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach

DVS-Voltmeter: Stochastic Process-Based Event Simulator for Dynamic Vision Sensors

Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal