Related papers: Removing Reflections from RAW Photos
Most vision models are trained on RGB images processed through ISP pipelines optimized for human perception, which can discard sensor-level information useful for machine reasoning. RAW images preserve unprocessed scene data, enabling…
We propose a new technique for estimating spatially varying parametric materials from a single image of an object with unknown shape in unknown illumination. Our method uses a low-order parametric reflectance model, and incorporates strong…
Environment maps are used to simulate reflections off curved objects. We present a technique to reflect a user, or a group of users, in a real environment, onto a virtual object, in a virtual reality application, using the live video feeds…
Estimating surface reflectance (BRDF) is one key component for complete 3D scene capture, with wide applications in virtual reality, augmented reality, and human computer interaction. Prior work is either limited to controlled environments…
RAW files are the initial measurement of scene radiance widely used in most cameras, and the ubiquitously-used RGB images are converted from RAW data through Image Signal Processing (ISP) pipelines. Nowadays, digital images are risky of…
Imaging under extremely low-light conditions presents a significant challenge and is an ill-posed problem due to the low signal-to-noise ratio (SNR) caused by minimal photon capture. Previously, diffusion models have been used for multiple…
Sensing and manipulating targets hidden under scattering media are universal problems that take place in applications ranging from deep-tissue optical imaging to laser surgery. A major issue in these applications is the shallow light…
While burst LR images are useful for improving the SR image quality compared with a single LR image, prior SR networks accepting the burst LR images are trained in a deterministic manner, which is known to produce a blurry SR image. In…
We present a method to remove, using only linear optics, exactly one photon from a field-mode. This is achieved by putting the system in contact with an absorbing environment which is under continuous monitoring. A feedback mechanism then…
High resolution image sensors require electrical access to each individual pixel for signal readout. Such access is especially challenging for ultra-miniaturized pixels, for heterogeneously integrated sensing and readout layers in…
Visual obstacle discovery is a key step towards autonomous navigation of indoor mobile robots. Successful solutions have many applications in multiple scenes. One of the exceptions is the reflective ground. In this case, the reflections on…
We address the problem of removing undesirable reflections from a single image captured through a glass surface, which is an ill-posed, challenging but practically important problem for photo enhancement. Inspired by iterative structure…
Unwanted camera occlusions, such as debris, dust, rain-drops, and snow, can severely degrade the performance of computer-vision systems. Dynamic occlusions are particularly challenging because of the continuously changing pattern. Existing…
State-of-the-art techniques for 3D reconstruction are largely based on volumetric scene representations, which require sampling multiple points to compute the color arriving along a ray. Using these representations for more general inverse…
Image de-blurring is important in many cases of imaging a real scene or object by a camera. This project focuses on de-blurring an image distorted by an out-of-focus blur through a simulation study. A pseudo-inverse filter is first explored…
Photometric stereo is a method that seeks to reconstruct the normal vectors of an object from a set of images of the object illuminated under different light sources. While effective in some situations, classical photometric stereo relies…
In real-world single image super-resolution (SISR) task, the low-resolution image suffers more complicated degradations, not only downsampled by unknown kernels. However, existing SISR methods are generally studied with the synthetic…
Creative processes such as painting often involve creating different components of an image one by one. Can we build a computational model to perform this task? Prior works often fail by making global changes to the image, inserting objects…
We consider solving ill-posed imaging inverse problems without access to an image prior or ground-truth examples. An overarching challenge in these inverse problems is that an infinite number of images, including many that are implausible,…
The Image Captioning (IC) technique is widely used to describe images in natural language. Recently, some IC system testing methods have been proposed. However, these methods still rely on pre-annotated information and hence cannot really…