Related papers: Self-Supervised Intrinsic Image Decomposition
Visual restoration and recognition are traditionally addressed in pipeline fashion, i.e. denoising followed by classification. Instead, observing correlations between the two tasks, for example clearer image will lead to better…
Image relighting is the task of showing what a scene from a source image would look like if illuminated differently. Inverse graphics schemes recover an explicit representation of geometry and a set of chosen intrinsics, then relight with…
Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end,…
Intrinsic image decomposition is a severely under-constrained problem. User interactions can help to reduce the ambiguity of the decomposition considerably. The traditional way of user interaction is to draw scribbles that indicate regions…
We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling…
Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems…
Inverse rendering, the process of inferring scene properties from images, is a challenging inverse problem. The task is ill-posed, as many different scene configurations can give rise to the same image. Most existing solutions incorporate…
Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…
We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation…
Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…
Retinal image matching plays a crucial role in monitoring disease progression and treatment response. However, datasets with matched keypoints between temporally separated pairs of images are not available in abundance to train…
The reconstruction of a high resolution image given a low resolution observation is an ill-posed inverse problem in imaging. Deep learning methods rely on training data to learn an end-to-end mapping from a low-resolution input to a…
Convolutional neural networks (CNNs) have been demonstrated their powerful ability to extract discriminative features for hyperspectral image classification. However, general deep learning methods for CNNs ignore the influence of complex…
Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo. This simulated data does not model many of the important…
We introduce Corrupted Image Modeling (CIM) for self-supervised visual pre-training. CIM uses an auxiliary generator with a small trainable BEiT to corrupt the input image instead of using artificial [MASK] tokens, where some patches are…
Traditional works have shown that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Make full use of these multi-scale information can improve…
Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…
In this paper, we tackle the problem of enhancing real-world low-light images with significant noise in an unsupervised fashion. Conventional unsupervised learning-based approaches usually tackle the low-light image enhancement problem…
This paper introduces the Raw Natural Image Noise Dataset (RawNIND), a diverse collection of paired raw images designed to support the development of denoising models that generalize across sensors, image development workflows, and styles.…
In this paper we examine the problem of inverse rendering of real face images. Existing methods decompose a face image into three components (albedo, normal, and illumination) by supervised training on synthetic face data. However, due to…