Learning sparse masks for diffusion-based image inpainting
Diffusion-based inpainting is a powerful tool for the reconstruction of images from sparse
data. Its quality strongly depends on the choice of known data. Optimising their spatial …
data. Its quality strongly depends on the choice of known data. Optimising their spatial …
Efficient data optimisation for harmonic inpainting with finite elements
V Chizhov, J Weickert - International Conference on Computer Analysis of …, 2021 - Springer
Harmonic inpainting with optimised data is very popular for inpainting-based image
compression. We improve this approach in three important aspects. Firstly, we replace the …
compression. We improve this approach in three important aspects. Firstly, we replace the …
Deep spatial and tonal data optimisation for homogeneous diffusion inpainting
Diffusion-based inpainting can reconstruct missing image areas with high quality from
sparse data, provided that their location and their values are well optimised. This is …
sparse data, provided that their location and their values are well optimised. This is …
Sparse inpainting with smoothed particle hydrodynamics
V Daropoulos, M Augustin, J Weickert - SIAM Journal on Imaging Sciences, 2021 - SIAM
Digital image inpainting refers to techniques used to reconstruct a damaged or incomplete
image by exploiting available image information. The main goal of this work is to perform the …
image by exploiting available image information. The main goal of this work is to perform the …
Exemplar-based image inpainting with multi-resolution information and the graph cut technique
H Liu, X Bi, G Lu, W Wang - IEEE Access, 2019 - ieeexplore.ieee.org
Filling holes in an image is achieved in a manner similar to peeling the onion. The order of
filling affects the image inpainting results, especially concerning the content of complex …
filling affects the image inpainting results, especially concerning the content of complex …
Interactive deep colorization and its application for image compression
Recent methods based on deep learning have shown promise in converting grayscale
images to colored ones. However, most of them only allow limited user inputs (no inputs …
images to colored ones. However, most of them only allow limited user inputs (no inputs …
A Wasserstein GAN for Joint Learning of Inpainting and Spatial Optimisation
P Peter - Pacific-Rim Symposium on Image and Video …, 2022 - Springer
Image inpainting is a restoration method that reconstructs missing image parts. However, a
carefully selected mask of known pixels that yield a high quality inpainting can also act as a …
carefully selected mask of known pixels that yield a high quality inpainting can also act as a …
Image Compression with Isotropic and Anisotropic Shepard Inpainting
Inpainting-based codecs store sparse selected pixel data and decode by reconstructing the
discarded image parts by inpainting. Successful codecs (coders and decoders) traditionally …
discarded image parts by inpainting. Successful codecs (coders and decoders) traditionally …
Optimising different feature types for inpainting-based image representations
F Jost, V Chizhov, J Weickert - ICASSP 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
Inpainting-based image compression is a promising alternative to classical transform-based
lossy codecs. Typically it stores a carefully selected subset of all pixel locations and their …
lossy codecs. Typically it stores a carefully selected subset of all pixel locations and their …
Efficient Parallel Algorithms for Inpainting-Based Representations of 4K Images--Part II: Spatial and Tonal Data Optimization
N Kämper, V Chizhov, J Weickert - arXiv preprint arXiv:2401.06747, 2024 - arxiv.org
Homogeneous diffusion inpainting can reconstruct missing image areas with high quality
from a sparse subset of known pixels, provided that their location as well as their gray or …
from a sparse subset of known pixels, provided that their location as well as their gray or …