Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that ...

Many natural objects, and in general layered materials, have non-linear reflection behaviour along the wavelengths. An accurate representation of phenomena such as interference and colour separation generally requires a fine spectral representation of light instead of the commonly used RGB components. In this article, we introduce and experiment with a general approach to create similar and con...

Chromatic adaptation transforms are used in imaging systems to map image appearance to colorimetry under different illumination sources. In this paper, the performance of different chromatic adaptation transforms (CAT) is compared with the performance of transforms based on RGB primaries that have been investigated in relation to standard color spaces for digital still camera characterization a...

This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps. It simultaneously performs training of two recurrent neural networks (RNNs) that are crossly connected through information transfer layers, which are learnt to adaptively extract relevant cross-modalit...

In this paper, we present a novel RGB-D SLAM system based on visual odometry and an extended information filter, which does not require any other sensors or odometry. In contrast to the graph optimization approaches, this is more suitable for online applications. A visual dead reckoning algorithm based on visual residuals is devised, which is used to estimate motion control input. In addition, ...

The paper presents a concept for generated motion maps to directly generate a human-specific modality such as human pose and stacked optical flow, with only one rgb-image. Although the conventional approaches have achieved a complicated estimation with a discriminative model, we find the solution with a recent generative model. The two primary contributions in this paper are as follows: (i) pro...

The paper presents an innovative approach to the spectral-based characterization of ink-jet color printers. Our objective was to design a color separation procedure based on a spectral model of the printer, managed here as an RGB device. The printer was a four-ink device, and we assumed that the driver always replaced the black completely when converting from RGB to CMYK amounts of ink. The col...