4 papers
TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation
Hyeonseop Song, Seokhun Choi, Hoseok Do
Large-vocabulary instance segmentation is constrained by long-tailed category distributions and fine-grained inter-class ambiguity. While data synthesis offers a promising alternat…
PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data
ChangHee Yang, Hyeonseop Song, Seokhun Choi +3
Despite considerable efforts to enhance the generalization of 3D pose estimators without costly 3D annotations, existing data augmentation methods struggle in real world scenarios…
Click-Gaussian: Interactive Segmentation to Any 3D Gaussians
Seokhun Choi, Hyeonseop Song, Jaechul Kim +2
Interactive segmentation of 3D Gaussians opens a great opportunity for real-time manipulation of 3D scenes thanks to the real-time rendering capability of 3D Gaussian Splatting. Ho…
Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation
Jihyun Kim, Changjae Oh, Hoseok Do +2
We present a new multi-modal face image generation method that converts a text prompt and a visual input, such as a semantic mask or scribble map, into a photo-realistic face image…