Yitong Wang

papers

909

total citations

papers (20)

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

ICCV 2025arXiv

citations

Universal Segmentation at Arbitrary Granularity with Language Instruction

CVPR 2024arXiv

citations

Structured Sparsity Learning for Efficient Video Super-Resolution

CVPR 2023arXiv

citations

LLMGA: Multimodal Large Language Model based Generation Assistant

ECCV 2024arXiv

citations

DreamOmni: Unified Image Generation and Editing

CVPR 2025arXiv

citations

Automatic Animation of Hair Blowing in Still Portrait Photos

ICCV 2023arXiv

citations

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

ECCV 2024arXiv

citations

DreamFuse: Adaptive Image Fusion with Diffusion Transformer

ICCV 2025arXiv

citations

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

ICCV 2025

citations

Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation

ICCV 2025arXiv

citations

Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors

AAAI 2025arXiv

citations

EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion

CVPR 2025

citations

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

ICCV 2025

citations

Yitong Wang

papers (20)

DiffIR: Efficient Diffusion Model for Image Restoration

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

Open-Vocabulary Segmentation with Semantic-Assisted Calibration

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

Global Spectral Filter Memory Network for Video Object Segmentation

Human De-Occlusion: Invisible Perception and Recovery for Humans

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

Universal Segmentation at Arbitrary Granularity with Language Instruction

Structured Sparsity Learning for Efficient Video Super-Resolution

LLMGA: Multimodal Large Language Model based Generation Assistant

DreamOmni: Unified Image Generation and Editing

Automatic Animation of Hair Blowing in Still Portrait Photos

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

DreamFuse: Adaptive Image Fusion with Diffusion Transformer

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation

Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors

EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

papers (20)

DiffIR: Efficient Diffusion Model for Image Restoration

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

Open-Vocabulary Segmentation with Semantic-Assisted Calibration

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

Global Spectral Filter Memory Network for Video Object Segmentation

Human De-Occlusion: Invisible Perception and Recovery for Humans

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

Universal Segmentation at Arbitrary Granularity with Language Instruction

Structured Sparsity Learning for Efficient Video Super-Resolution

LLMGA: Multimodal Large Language Model based Generation Assistant

DreamOmni: Unified Image Generation and Editing

Automatic Animation of Hair Blowing in Still Portrait Photos

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

DreamFuse: Adaptive Image Fusion with Diffusion Transformer

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation

Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors

EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing