Soo Ye Kim

sooyek's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 10 papers 1 day ago

OmniXRef: A Unified Framework for Multimodal Multi-Reference Video Editing

Paper • 2610.22744 • Published 7 days ago • 20

OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation

Paper • 2510.24093 • Published Oct 28, 2025

PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models

Paper • 2602.20583 • Published Feb 24

RefGC-SR$^2$: Reference-guided Generated Content Super-Resolution and Refinement

Paper • 2606.15158 • Published Jun 13 • 10

Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing

Paper • 2606.01079 • Published May 31

MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

Paper • 2604.00853 • Published Apr 1

Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion

Paper • 2603.15614 • Published Mar 16 • 7

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Paper • 2512.17909 • Published Dec 19, 2025 • 37

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

Paper • 2506.23361 • Published Jun 29, 2025 • 1

Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model

Paper • 2402.05350 • Published Feb 8, 2024

upvoted a paper 2 days ago

OmniXRef: A Unified Framework for Multimodal Multi-Reference Video Editing

Paper • 2610.22744 • Published 7 days ago • 20

updated a dataset about 1 year ago

sooyek/EditVerseBench

Viewer • Updated Oct 9, 2025 • 1.61k • 565 • 5

New activity in sooyek/EditVerseBench about 1 year ago

Update README.md

#1 opened about 1 year ago by

juxuan27

published a dataset about 1 year ago

sooyek/EditVerseBench

Viewer • Updated Oct 9, 2025 • 1.61k • 565 • 5

upvoted a paper about 1 year ago

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning

Paper • 2509.20360 • Published Sep 24, 2025 • 18

authored 5 papers about 1 year ago

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning

Paper • 2509.20360 • Published Sep 24, 2025 • 18

ObjectStitch: Generative Object Compositing

Paper • 2212.00932 • Published Dec 2, 2022

Thinking Outside the BBox: Unconstrained Generative Object Compositing

Paper • 2409.04559 • Published Sep 6, 2024

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation

Paper • 2411.14384 • Published Nov 21, 2024 • 9

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

Paper • 2412.02635 • Published Dec 3, 2024 • 1