Spatial Pattern Templates for Recognition of Objects with Regular Structure

By Radim Tylecek, Radim Sára. 2013

378 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks (2017, neutral): “Figure 8 shows some example results on other paired datasets used in “pix2pix” [18], such as architectural labels↔photos from the CMP Facade Database [34], and edges↔shoes from the UT Zappos50K dataset [53].”
Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation (2021, methodology): “We first demonstrate the effectiveness of Piggyback GAN on 4 tasks of paired image-conditioned generation, which are all image-to-image translations, on challenging domains and datasets with large variation across different modalities [9,14,35,39].”
Lifelong GAN: Continual Learning for Conditional Image Generation (2019, background): “The second task is image-to-image translation of segmentations → facades [27].”
DualGAN: Unsupervised Dual Learning for Image-to-Image Translation (2017, methodology): “To compare DualGAN with GAN and cGAN [4], four labeled datasets are used: PHOTO-SKETCH [22, 25], DAY-NIGHT [5], LABEL-FACADES [20], and AERIALMAPS, which was directly captured from Google Map [4].”
3D all the way: Semantic segmentation of urban scenes from start to end in 3D (2015, neutral): “[48] model alignment and repetition through spatial relations in a CRF framework.”
One-Shot Unsupervised Cross Domain Translation (2018, methodology): “Drawing Tasks We consider the translation of Google Maps to Aerial View photos [23], Facades to Images [28], Cityscapes to Labels [29] and the reverse translations.”
On the Evaluation of Conditional GANs (2019, background): “Table 3 provides the FJD, FID, and SSIM scores for state-of-the-art models on four different image-to-image datasets: Facades [31], Maps [16], Edges2Shoes and Edges2Handbag [56].6 We consider the validation set associated with each of the datasets and obtain one sample per conditioning for each mode”
Delving Deeper into Anti-Aliasing in ConvNets (2020, methodology): “Experiment Settings We evaluate image-to-image translation on the Cityscapes [12] and Facades [61] datasets using Pix2PixHD [67] and Pix2Pix [27] as the baseline models, respectively.”
Focal Frequency Loss for Image Reconstruction and Synthesis (2020, methodology): “For pix2pix image-to-image translation, we utilize the officially prepared CMP Facades [23] dataset.”
Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting (2019, background): “– Facade [25]: a collection of highly-structured facades from different cities around the world.”
UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models (2021, methodology): “Facade The (A) photo and (B) semantic segmentation label images of buildings from the CMP Facades dataset [39].”
Efficient 2D and 3D Facade Segmentation Using Auto-Context (2016, neutral): “The work of [2] uses long-range pairwise and ternary potentials to encode the repetitive nature of various class regions.”
Image-to-image translation for cross-domain disentanglement (2018, methodology): “Table 1 (right) presents results using the provided train/test splits (100 test images for Facades and 1K for Maps) and the available pre-trained BicycleGAN models [49].”
Learning Texture Manifolds with the Periodic Spatial GAN (2017, methodology): “The following image sources were used for the experiments in this paper: the Oxford Describable Textures Dataset (DTD) (Cimpoi et al., 2014), which is composed of various categories, each containing 120 images; the Facades dataset (Radim Tyle ˇ cek, 2013), which contains 500 facades of different hou”