paper-with-me

홈 › Papers

Dual-Path Image Inpainting With Auxiliary GAN Inversion

2022-01-01 · CVPR 2022 1 · Wentao Wang, Li Niu, Jianfu Zhang, Xue Yang, Liqing Zhang

Deep image inpainting can inpaint a corrupted image using a feed-forward inference, but still fails to handle large missing area or complex semantics. Recently, GAN inversion based inpainting methods propose to leverage semantic information in pretrained generator (e.g., StyleGAN) to solve the above issues. Different from feed-forward methods, they seek for a closest latent code to the corrupted image and feed it to a pretrained generator. However, inferring the latent code is either time-consuming or inaccurate. In this paper, we develop a dual-path inpainting network with inversion path and feed-forward path, in which inversion path provides auxiliary information to help feed-forward path. We also design a novel deformable fusion module to align the feature maps in two paths. Experiments on FFHQ and LSUN demonstrate that our method is effective in solving the aforementioned problems while producing more realistic results than state-of-the-art methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Image Inpainting

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion

2025-04-17 · Libo Zhang, Yongsheng Yu, Jiali Yao, Heng Fan

Generative Adversarial Network (GAN) inversion have demonstrated excellent performance in image inpainting that aims to restore lost or damaged image texture using its unmasked content. Previous GAN inversion-based metho…

Generative Adversarial NetworkImage InpaintingSemantic Segmentation

Prompt-Guided Dual Latent Steering for Inversion Problems

2025-09-23 · Yichen Wu, Xu Liu, Chenxuan Zhao, Xinyu Wu arxiv

Inverting corrupted images into the latent space of diffusion models is challenging. Current methods, which encode an image into a single latent vector, struggle to balance structural fidelity with semantic accuracy, lea…

BrushEdit: All-In-One Image Inpainting and Editing

2024-12-13 · Yaowei Li, Yuxuan Bian, Xuan Ju, Zhaoyang Zhang 외

Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g…

AllImage Inpainting

High-Fidelity Image Inpainting with GAN Inversion

2022-08-25 · Yongsheng Yu, Libo Zhang, Heng Fan, Tiejian Luo

Image inpainting seeks a semantically consistent way to recover the corrupted image in the light of its unmasked content. Previous approaches usually reuse the well-trained GAN as effective prior to generate realistic pa…

Image InpaintingVocal Bursts Intensity Prediction

Unpaired Multi-Domain Histopathology Virtual Staining using Dual Path Prompted Inversion

2024-12-15 · Bing Xiong, Yue Peng, Ranran Zhang, Fuqiang Chen 외

Virtual staining leverages computer-aided techniques to transfer the style of histochemically stained tissue samples to other staining types. In virtual staining of pathological images, maintaining strict structural cons…

DiagnosticDisentanglementPrompt LearningStyle Transfer+1