Miguel Granados

Optimal HDR reconstruction with linear digital cameras

Given a multi-exposure sequence of a scene, our aim is to recover the absolute irradiance falling onto a linear camera sensor. The established approach is to perform a weighted average of the scaled input exposures. However, there is no clear consensus on the appropriate weighting to use. We propose a weighting function that produces statistically optimal estimates under the assumption of compound-Gaussian noise. Our weighting is based on a calibrated camera model that accounts for all noise sources. This model also allows us to simultaneously estimate the irradiance and its uncertainty. We evaluate our method on simulated and real world photographs, and show that we consistently improve the signal-to-noise ratio over previous approaches. Finally, we show the effectiveness of our model for optimal exposure sequence selection and HDR image denoising.

Boolean operations on 3D selective Nef complexes : data structure, algorithms, and implementation

We describe a data structure for three-dimensional Nef complexes, algorithms for boolean operations on them, and our implementation of data structure and algorithms. Nef polyhedra were introduced by W. Nef in his seminal 1978 book on polyhedra. They are the closure of half-spaces under boolean operations and can represent non-manifold situations, open and closed boundaries, and mixed dimensional complexes. Our focus lies on the generality of the data structure, the completeness of the algorithms, and the exactness and efficiency of the implementation. In particular, all degeneracies are handled.

Background inpainting for videos with dynamic objects and a free-moving camera

We propose a method for removing marked dynamic objects from videos captured with a free-moving camera, so long as the objects occlude parts of the scene with a static background. Our approach takes as input a video, a mask marking the object to be removed, and a mask marking the dynamic objects to remain in the scene. To inpaint a frame, we align other candidate frames in which parts of the missing region are visible. Among these candidates, a single source is chosen to fill each pixel so that the final arrangement is color-consistent. Intensity differences between sources are smoothed using gradient domain fusion. Our frame alignment process assumes that the scene can be approximated using piecewise planar geometry: A set of homographies is estimated for each frame pair, and one each is selected for aligning pixels such that the color-discrepancy is minimized and the epipolar constraints are maintained. We provide experimental validation with several real-world video sequences to demonstrate that, unlike in previous work, inpainting videos shot with free-moving cameras does not necessarily require estimation of absolute camera positions and per-frame per-pixel depth maps.

How Not to Be Seen — Object Removal from Videos of Crowded Scenes

Removing dynamic objects from videos is an extremely challenging problem that even visual effects professionals often solve with time‐consuming manual frame‐by‐frame editing. We propose a new approach to video completion that can deal with complex scenes containing dynamic background and non‐periodical moving objects. We build upon the idea that the spatio‐temporal hole left by a removed object can be filled with data available on other regions of the video where the occluded objects were visible. Video completion is performed by solving a large combinatorial problem that searches for an optimal pattern of pixel offsets from occluded to unoccluded regions. Our contribution includes an energy functional that generalizes well over different scenes with stable parameters, and that has the desirable convergence properties for a graph‐cut‐based optimization. We provide an interface to guide the completion process that both reduces computation time and allows for efficient correction of small errors in the result. We demonstrate that our approach can effectively complete complex, high‐resolution occlusions that are greater in difficulty than what existing methods have shown.

Contrast-Use Metrics for Tone Mapping Images

Existing tone mapping operators (TMOs) provide good results in well-lit scenes, but often perform poorly on images in low light conditions. In these scenes, noise isprevalent and gets amplified by TMOs, as they confuse contrast created by noise with contrast created by the scene. This paper presents a principled approach to produce tone mapped images with less visible noise. For this purpose, we leverage established models of camera noise and human contrast perception to design two new quality scores: contrast waste and contrast loss, which measure image quality as a function of contrast allocation. To produce tone mappings with less visible noise, we apply these scores in two ways: first, to automatically tune the parameters of existing TMOs to reduce the amount of noise they produce; and second, to propose a new noise-aware tone curve.

HDR image noise estimation for denoising tone mapped images

Tone mapping operators are designed to compress the dynamic range of high dynamic range (HDR) images while preserving the perceived image brightness, but they often enhance image noise in the process, specially in low-light conditions. We propose a method for reducing noise in images created by any tone mapping operator. Our approach leverages the noise distribution of the HDR image to guide the range kernel of a cross bilateral filter that is used to denoise the tone mapped image. When the noise distribution is unknown, we use a new method to automatically estimate it assuming that the HDR image was produced as an average of multiple exposures taken in RAW or JPEG compressed format. Our method performs quantitatively better than existing denoising methods applied on either the original HDR or the tone-mapped images directly, and a user study confirms that it produces visually preferable results.