CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying

by   Weihuang Liu, et al.

Image inpainting aims to fill the missing hole of the input. It is hard to solve this task efficiently when facing high-resolution images due to two reasons: (1) Large reception field needs to be handled for high-resolution image inpainting. (2) The general encoder and decoder network synthesizes many background pixels synchronously due to the form of the image matrix. In this paper, we try to break the above limitations for the first time thanks to the recent development of continuous implicit representation. In detail, we down-sample and encode the degraded image to produce the spatial-adaptive parameters for each spatial patch via an attentional Fast Fourier Convolution(FFC)-based parameter generation network. Then, we take these parameters as the weights and biases of a series of multi-layer perceptron(MLP), where the input is the encoded continuous coordinates and the output is the synthesized color value. Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing. Then, the continuous position encoding will be helpful to synthesize the photo-realistic high-frequency textures by re-sampling the coordinate in a higher resolution. Also, our framework enables us to query the coordinates of missing pixels only in parallel, yielding a more efficient solution than the previous methods. Experiments show that the proposed method achieves real-time performance on the 2048×2048 images using a single GTX 2080 Ti GPU and can handle 4096×4096 images, with much better performance than existing state-of-the-art methods visually and numerically. The code is available at:


page 1

page 3

page 5

page 7


Deep Two-Stage High-Resolution Image Inpainting

In recent years, the field of image inpainting has developed rapidly, le...

Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting

Recently data-driven image inpainting methods have made inspiring progre...

Resolution-robust Large Mask Inpainting with Fourier Convolutions

Modern image inpainting systems, despite the significant progress, often...

Large Hole Image Inpainting With Compress-Decompression Network

Image inpainting technology can patch images with missing pixels. Existi...

Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization

Image harmonization aims to modify the color of the composited region wi...

Implicit Neural Feature Fusion Function for Multispectral and Hyperspectral Image Fusion

Multispectral and Hyperspectral Image Fusion (MHIF) is a practical task ...

Coordinate Quantized Neural Implicit Representations for Multi-view Reconstruction

In recent years, huge progress has been made on learning neural implicit...

Please sign up or login with your details

Forgot password? Click here to reset