paper-with-me

홈 › Papers

FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting

2021-08-10 · Junke Wang, Shaoxiang Chen, Zuxuan Wu, Yu-Gang Jiang

Blind face inpainting refers to the task of reconstructing visual contents without explicitly indicating the corrupted regions in a face image. Inherently, this task faces two challenges: (1) how to detect various mask patterns of different shapes and contents; (2) how to restore visually plausible and pleasing contents in the masked regions. In this paper, we propose a novel two-stage blind face inpainting method named Frequency-guided Transformer and Top-Down Refinement Network (FT-TDR) to tackle these challenges. Specifically, we first use a transformer-based network to detect the corrupted regions to be inpainted as masks by modeling the relation among different patches. We also exploit the frequency modality as complementary information for improved detection results and capture the local contextual incoherence to enhance boundary consistency. Then a top-down refinement network is proposed to hierarchically restore features at different levels and generate contents that are semantically consistent with the unmasked face regions. Extensive experiments demonstrate that our method outperforms current state-of-the-art blind and non-blind face inpainting methods qualitatively and quantitatively.

📄 PDF Abstract BibTeX arXiv:2108.04424

Code (0)

등록된 구현이 없습니다.

Tasks

Facial Inpainting

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

WaveDH: Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazing

2024-04-02 · Seongmin Hwang, Daeyoung Han, Cheolkon Jung, Moongu Jeon

The surge in interest regarding image dehazing has led to notable advancements in deep learning-based single image dehazing approaches, exhibiting impressive performance in recent studies. Despite these strides, many exi…

Image DehazingSingle Image Dehazing

I2V: Towards Texture-Aware Self-Supervised Blind Denoising using Self-Residual Learning for Real-World Images

2023-02-21 · Kanggeun Lee, Kyungryun Lee, Won-Ki Jeong

Although the advances of self-supervised blind denoising are significantly superior to conventional approaches without clean supervision in synthetic noise scenarios, it shows poor quality in real-world images due to spa…

DenoisingSSIM

Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network

2023-04-19 · ICCV 2023 1 · Yeong Il Jang, Keuntek Lee, Gu Yong Park, Seyun Kim 외

There have been many image denoisers using deep neural networks, which outperform conventional model-based methods by large margins. Recently, self-supervised methods have attracted attention because constructing a large…

DenoisingImage Denoising

HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing

2026-04-04 · Mohammad Heydari, Wei Dong, Shahram Shirani, Jun Chen 외 arxiv

Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly u…

Representation LearningImage Dehazing

Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution

2023-08-09 · ICCV 2023 10 · Ao Li, Le Zhang, Yun Liu, Ce Zhu

Transformer-based methods have exhibited remarkable potential in single image super-resolution (SISR) by effectively extracting long-range dependencies. However, most of the current research in this area has prioritized …

Image Super-ResolutionQuantizationSuper-Resolution