Generally, image-to-image translation (i2i) methods aim at learning mapp...
Because of the diversity in lighting environments, existing illumination...
Light plays an important role in human well-being. However, most compute...
Wide-angle lenses are commonly used in perception tasks requiring a larg...
GAN-based image restoration inverts the generative process to repair ima...
We present LM-GAN, an HDR sky model that generates photorealistic enviro...
Most camera lens systems are designed in isolation, separately from
down...
We present a method for estimating lighting from a single perspective im...
Image editing and compositing have become ubiquitous in entertainment, f...
We present PanoHDR-NeRF, a novel pipeline to casually capture a plausibl...
Adaptive instance normalization (AdaIN) has become the standard method f...
Scene inference under low-light is a challenging problem due to severe n...
Deep generative models like StyleGAN hold the promise of semantic image
...
In image classification, it is common practice to train deep networks to...
Most image-to-image translation methods require a large number of traini...
Most image-to-image translation methods focus on learning mappings acros...
We introduce Persistent Mixture Model (PMM) networks for representation
...
Recent work has demonstrated that deep learning approaches can successfu...
Rain fills the atmosphere with water particles, which breaks the common
...
Augmented reality devices require multiple sensors to perform various ta...
Computer vision datasets containing multiple modalities such as color, d...
Few-shot image classification aims at training a model by using only a f...
Detecting objects in images is a quintessential problem in computer visi...
We present a method to estimate lighting from a single image of an indoo...
To improve the robustness to rain, we present a physically-based rain
re...
We present a neural network that predicts HDR outdoor illumination from ...
We propose a real-time method to estimate spatiallyvarying indoor lighti...
Relighting is an essential step in artificially transferring an object f...
We propose a data-driven learned sky model, which we use for outdoor lig...
Predicting the short-term power output of a photovoltaic panel is an
imp...
In this work, we propose a step towards a more accurate prediction of th...
Drastic variations in illumination across surveillance cameras make the
...
Photometric Stereo in outdoor illumination remains a challenging, ill-po...
We present a challenging and realistic novel dataset for evaluating 6-DO...
Most current single image camera calibration methods rely on specific im...
We propose an automatic method to infer high dynamic range illumination ...
Outdoor lighting has extremely high dynamic range. This makes the proces...
We present a temporal 6-DOF tracking method which leverages deep learnin...
We present a CNN-based technique to estimate high-dynamic range outdoor
...