Related papers: Computational Flash Photography through Intrinsics
Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the…
In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in…
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…
We present photonic quantum computing architectures that can deal with both probabilistic (heralded) generation of single photons and probabilistic gates without making use of coherent switching. The only required dynamical element is the…
Photonic entanglement has a wide range of applications in quantum computation and communication. Here we introduce a new device: the "photonic module", which allows for the rapid, deterministic preparation of a large class of entangled…
Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by…
We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e.g. through text or environment maps), accumulate errors when chaining inverse…
This paper presents a novel intrinsic image transfer (IIT) algorithm for illumination manipulation, which creates a local image translation between two illumination surfaces. This model is built on an optimization-based framework consisting…
Context. Solar wavefront sensing has been a challenge for astrophysical instrumentalists, due to the low contrast between the Sun and the sky background compared to night-time observations, which limits the performance of adaptive optics…
Photography usually requires optics in conjunction with a recording device (an image sensor). Eliminating the optics could lead to new form factors for cameras. Here, we report a simple demonstration of imaging using a bare CMOS sensor that…
Authoring high-quality digital materials is key to realism in 3D rendering. Previous generative models for materials have been trained exclusively on synthetic data; such data is limited in availability and has a visual gap to real…
Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse…
Blur is an image degradation that is difficult to remove. Invariants with respect to blur offer an alternative way of a~description and recognition of blurred images without any deblurring. In this paper, we present an original unified…
We describe a technique for generating pulses of light with controllable photon numbers, propagation direction, timing, and pulse shapes. The technique is based on preparation of an atomic ensemble in a state with a desired number of atomic…
Fluorescent imaging plays a critical role in a myriad of scientific endeavors, particularly in the biological sciences. Three-dimensional imaging of fluorescent intensity often requires serial data acquisition, that is voxel-by-voxel…
Identifying firefly flashes from other bright features in nature images is complicated. I provide a training dataset and trained neural networks for reliable flash classification. The training set consists of thousands of cropped images…
We present a method to separate a single image captured under two illuminants, with different spectra, into the two images corresponding to the appearance of the scene under each individual illuminant. We do this by training a deep neural…
We propose a novel intrinsic image decomposition network considering reflectance consistency. Intrinsic image decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as…
Recent methods have shown that pre-trained diffusion models can be fine-tuned to enable generative inverse rendering by learning image-conditioned noise-to-intrinsic mapping. Despite their remarkable progress, they struggle to robustly…
Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion…