4 papers
CorrFill: Enhancing Faithfulness in Reference-based Inpainting with Correspondence Guidance in Diffusion Models
Kuan-Hung Liu, Cheng-Kun Yang, Min-Hung Chen +2
In the task of reference-based image inpainting, an additional reference image is provided to restore a damaged target image to its original state. The advancement of diffusion mod…
ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
Chi-Wei Hsiao, Yu-Lun Liu, Cheng-Kun Yang +3
While recent works on blind face image restoration have successfully produced impressive high-quality (HQ) images with abundant details from low-quality (LQ) input images, the gene…
PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation
Ardian Umam, Cheng-Kun Yang, Min-Hung Chen +2
This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation. Par…
2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision
Cheng-Kun Yang, Min-Hung Chen, Yung-Yu Chuang +1
We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and 3D data for weakly supervised point cloud segmentation. Research studies have shown that 2D and 3…