Visual Chirality

  title={Visual Chirality},
  author={Zhiqiu Lin and Jin Sun and Abe Davis and Noah Snavely},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Zhiqiu Lin, J. Sun, +1 author Noah Snavely
  • Published 1 June 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
How can we tell whether an image has been mirrored? While we understand the geometry of mirror reflections very well, less has been said about how it affects distributions of imagery at scale, despite widespread use for data augmentation in computer vision. In this paper, we investigate how the statistics of visual data are changed by reflection. We refer to these changes as ``visual chirality,'' after the concept of geometric chirality---the notion of objects that are distinct from their… 
Dissecting Image Crops
The aim of this work is to dissect the fundamental impact of spatial crops, and there are also a number of practical implications to the work, such as detecting image manipulations and equipping neural network researchers with a better understanding of shortcut learning.
Insights From A Large-Scale Database of Material Depictions In Paintings
It is found that visual recognition systems designed for natural images can work surprisingly well on paintings and it is shown that learning from paintings can be beneficial for neural networks that are intended to be used on natural images.
Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting
Although CNNs have achieved remarkable progress on the shadow detection task, they tend to make mistakes in dark non-shadow regions and relatively bright shadow regions. They are also susceptible to
A novel approach to generating high-resolution adversarial examples
This work proposes a feasible approach, which improves on the AdvGAN framework through data augmentation, combined with PCA and KPCA to map the input instance’s main features onto the latent variables, and can generate strongly semantically adversarial examples with better transferability on prevailing DNNs classification models.


Many natural shapes have chirality (or handedness): for instance our hands have a right-hand version and a left-hand version, the two types being mirror images of each other. In chemistq, for
BubbLeNet: Foveated Imaging for Visual Discovery
A new technique that uses bubble images -- images where most of the content has been obscured -- to identify spatially localized, discriminative content in each image is proposed, which retains much of the original classification performance, but is much more amenable to identifying interpretable visual elements.
Learning and Using the Arrow of Time
A ConvNet suitable for extended temporal footprints and for class activation visualization, and the effect of artificial cues, such as cinematographic conventions, on learning is studied, which achieves state-of-the-art performance on large-scale real-world video datasets.
Seeing the Arrow of Time
Good video forwards/backwards classification results are demonstrated on a selection of YouTube video clips, and on natively-captured sequences (with no temporally-dependent video compression), and what motions the models have learned that help discriminate forwards from backwards time are examined.
Computational Symmetry in Computer Vision and Computer Graphics
Recognizing the fundamental relevance and group theory of symmetry has the potential to play an important role in computational sciences.
Unsupervised Representation Learning by Predicting Image Rotations
This work proposes to learn image features by training ConvNets to recognize the 2d rotation that is applied to the image that it gets as input, and demonstrates both qualitatively and quantitatively that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning.
A Century of Portraits: A Visual Historical Record of American High School Yearbooks
A dataset of 37,921 frontal-facing American high school yearbook photos is presented that allows us to use computation to glimpse into the historical visual record too voluminous to be evaluated manually and may be used together with weakly-supervised data-driven techniques to perform scalable historical analysis of large image corpora with minimal human effort.
What makes Paris look like Paris?
It is shown that geographically representative image elements can be discovered automatically from Google Street View imagery in a discriminative manner and it is demonstrated that these elements are visually interpretable and perceptually geo-informative.
Upright orientation of man-made objects
This paper shows that it is often possible to infer a shape's upright orientation by analyzing its geometry, and reduces the two-dimensional orientation space to a small set of orientation candidates using functionality-related geometric properties of the object, and determines the best orientation using an assessment function of several functional geometric attributes defined with respect to each candidate.
Unsupervised Visual Representation Learning by Context Prediction
It is demonstrated that the feature representation learned using this within-image context indeed captures visual similarity across images and allows us to perform unsupervised visual discovery of objects like cats, people, and even birds from the Pascal VOC 2011 detection dataset.