Transient attributes for high-level understanding and editing of outdoor scenes

By Pierre-Yves Laffont, Zhile Ren, Xiaofeng Tao, Chao Qian, James Hays. 2014

208 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

Image-to-Image Translation with Conditional Adversarial Networks (2016, background): “, [14, 23, 18, 8, 10, 50, 30, 36, 16, 55, 58]), despite the fact that the setting is always the same: predict pixels from pixels.”
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks (2017, background): “Years of research in computer vision, image processing, computational photography, and graphics have produced powerful translation systems in the supervised setting, where example image pairs { x, y } are available (Figure 2, left), e.g., [10, 18, 21, 22, 26, 31, 44, 55, 57, 61].”
Toward Multimodal Image-to-Image Translation (2017, methodology): “Datasets We test our method on several image-to-image translation problems from prior work, including edges→ photos [48, 54], Google maps→ satellite [20], labels→ images [5], and outdoor night→ day images [25].”
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].”
GP-GAN: Towards Realistic High-Resolution Image Blending (2017, methodology): “We randomly generate 150K images from Transient Attributes Database using the central-squared patch as the mask.”
Deep Feature Interpolation for Image Content Changes (2016, background): “Examples include transformations of human faces [41, 17], materials [2, 1], color [50], or seasons in outdoor images [23].”
TILDE: A Temporally Invariant Learned DEtector (2014, background): “However, their advantages are not easily carried on to the problem we tackle here, such as finding similar outdoors scenes [19].”
Manipulating Attributes of Natural Scenes via Hallucination (2018, methodology): “2017] and Transient Attributes [Laffont et al. 2014]—for reasons that will become clear shortly.”
24/7 Place Recognition by View Synthesis (2018, unknown): “Removing the artifacts altogether, for example by using multiple images [49], [50], [62] combined with”
Positional Normalization (2019, methodology): “Here we conduct experiments on whether PONO-MS helps Pix2pix [30] with Maps [79], Cityscapes [10] and Day ↔ Night [38].”
Improving Shape Deformation in Unsupervised Image-to-Image Translation (2018, methodology): “The approach relies on non-parametric texture synthesis and can handle transformations such as seasonal scene shifts [22], color and texture transformation, and painterly style transfer.”
Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images (2016, methodology): “Some target a specific domain and attribute, such as methods to enhance the “memorability” [17] or age [16] of facial photos, or to edit outdoor scenes with transient attributes like weather [22].”
DoveNet: Deep Image Harmonization via Domain Verification (2019, methodology): “Finally, we choose day2night dataset [18], because day2night provides a collection of aligned images captured in a variety of conditions (e.”
Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation (2021, unknown): “, 2016) for attribute prediction on the Transient Attribute (Laffont et al., 2014) and the CelebA (Liu et al.”