Silvano Galliani

Learn More
We present a new, massively parallel method for high-quality multiview matching. Our work builds on the Patchmatch idea: starting from randomly generated 3D planes in scene space, the best-fitting planes are iteratively propagated and refined to obtain a 3D depth and normal field per view, such that a robust photo-consistency measure over all images is(More)
We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries. Semantic segmentation is a fundamental remote sensing task, and most state-of-the-art methods rely on DCNNs as their workhorse. A major reason for their success is that deep networks learn to(More)
Since the integration of normal vectors plays an important role for reconstructing a surface, over decades it has been one of the most fundamental problems in computer vision and thereby extensively investigated by many researchers [6]. While many schemes have been proposed, there is, however, still a need for methods that combine accuracy, robustness and(More)
This report documents the program and the results of Dagstuhl Seminar 11142 Innovations for Shape Analysis: Models and Algorithms, taking place April 3-8 in 2011. The focus of the seminar was to discuss modern and emerging topics in shape analysis by researchers from different scientific communities, as there is no conference specifically devoted to this(More)
We describe a novel method for blind, single-image spectral super-resolution. While conventional superresolution aims to increase the spatial resolution of an input image, our goal is to spectrally enhance the input, i.e., generate an image with the same spatial resolution, but a greatly increased number of narrow (hyper-spectral) wavelength bands. Just(More)
We present a multi-view reconstruction method that combines conventional multi-view stereo (MVS) with appearance-based normal prediction, to obtain dense and accurate 3D surface models. Reliable surface normals reconstructed from multi-view correspondence serve as training data for a convolutional neural network (CNN), which predicts continuous normal(More)
In the last four decades there has been enormous progress in Shape from Shading (SfS) with respect to both modelling and numerics. In particular approaches based on advanced model assumptions such as perspective cameras and non-Lambertian surfaces have become very popular. However, regarding the positioning of the light source, almost all recent approaches(More)
Motivated by the limitations of existing multi-view stereo benchmarks, we present a novel dataset for this task. Towards this goal, we recorded a variety of indoor and outdoor scenes using a high-precision laser scanner and captured both high-resolution DSLR imagery as well as synchronized low-resolution stereo videos with varying fieldsof-view. To align(More)
Due to their improved capability to handle realistic illumination scenarios, nonLambertian reflectance models are becoming increasingly more popular in the Shape from Shading (SfS) community. One of these advanced models is the Oren-Nayar model which is particularly suited to handle rough surfaces. However, not only the proper selection of the model is(More)
We show images of all 14 initial scenes in our benchmark in Fig. 1. They consist of 7 outdoor and 7 indoor scenes. Numerous scenes contain thin structures such as the trees in forest, or a rope in playground. Several scenes also contain large homogeneous or reflective surfaces such as the floor in pipes and terrains, the walls in office, or some doors in(More)