Jaegul Choo

16

Papers

220

Total Citations

Papers (16)

StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

Sparse autoencoders reveal selective remapping of visual concepts during adaptation

Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair

What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer

iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds

Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention

Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision

Zero-Shot Head Swapping in Real-World Scenarios

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks

Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention

PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask

Enabling Region-Specific Control via Lassos in Point-Based Colorization

MagiCapture: High-Resolution Multi-Concept Portrait Customization

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling