Related papers: Environment Maps Editing using Inverse Rendering a…
While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…
It is essential to have a method to map an unknown terrain for various applications. For places where human access is not possible, a method should be proposed to identify the environment. Exploration, disaster relief, transportation and…
We introduce an approach for the real-time (2Hz) creation of a dense map and alignment of a moving robotic agent within that map by rendering using a Graphics Processing Unit (GPU). This is done by recasting the scan alignment part of the…
Inverse rendering aims to reconstruct geometry and reflectance from captured images. Display-camera imaging systems offer unique advantages for this task: each pixel can easily function as a programmable point light source, and the…
This paper presents an innovative in-pixel contrast enhancement circuit that performs image processing directly within the pixel circuit. The circuit can be tuned for different modes of operation. In foreground enhancement mode, it…
In the field of computer vision, visible light images often exhibit low contrast in low-light conditions, presenting a significant challenge. While infrared imagery provides a potential solution, its utilization entails high costs and…
Achieving physically consistent image editing remains a significant challenge in computer vision. Existing image editing methods typically rely on neural networks, which struggle to accurately handle shadows and refractions. Conversely,…
High dynamic range (HDR) imagery offers a rich and faithful representation of scene radiance, but remains challenging for generative models due to its mismatch with the bounded, perceptually compressed data on which these models are…
Deep learning-based (DL-based) hyperspectral image (HIS) super-resolution (SR) methods have achieved remarkable performance and attracted attention in industry and academia. Nonetheless, most current methods explored and learned the mapping…
Snapshot HDR imaging is essential to capture the full dynamic range of a scene in a single exposure, making it essential for video and dynamic environments where motion prevents the use of multi-exposure techniques or complex hardware…
Previous face inverse rendering methods often require synthetic data with ground truth and/or professional equipment like a lighting stage. However, a model trained on synthetic data or using pre-defined lighting priors is typically unable…
Hyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information about the material composition of the imaged scene. However, these images can be affected by various sources of…
Existing methods for relightable view synthesis -- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoints under a target illumination -- are based on inverse…
Image foreground extraction is a classical problem in image processing and vision, with a large range of applications. In this dissertation, we focus on the extraction of text and graphics in mixed-content images, and design novel…
Current differentiable renderers provide light transport gradients with respect to arbitrary scene parameters. However, the mere existence of these gradients does not guarantee useful update steps in an optimization. Instead, inverse…
Blind image deblurring is a long standing challenging problem in image processing and low-level vision. Recently, sophisticated priors such as dark channel prior, extreme channel prior, and local maximum gradient prior, have shown promising…
Images acquired during underwater activities suffer from environmental properties of the water, such as turbidity and light attenuation. These phenomena cause color distortion, blurring, and contrast reduction. In addition, irregular…
Natural images tend to mostly consist of smooth regions with individual pixels having highly correlated spectra. This information can be exploited to recover hyperspectral images of natural scenes from their incomplete and noisy…
In this work, we address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image. Most existing methods formulate the task as image-to-image translation, ignoring the 3D properties of…
We present a efficient multi-view inverse rendering method for large-scale real-world indoor scenes that reconstructs global illumination and physically-reasonable SVBRDFs. Unlike previous representations, where the global illumination of…