Section: New Results

High-Resolution Scene Reconstruction

We addressed the problem of range-stereo fusion for the construction of high-resolution depth maps. In particular, we combine low-resolution depth data with high-resolution stereo data, in a maximum a posteriori (MAP) formulation. Unlike existing schemes that build on MRF optimizers, we infer the disparity map from a series of local energy minimization problems that are solved hierarchically, by growing sparse initial disparities obtained from the depth data. The accuracy of the method is not compromised, owing to three properties of the data-term in the energy function. Firstly, it incorporates a new correlation function that is capable of providing refined correlations and disparities, via sub-pixel correction. Secondly, the correlation scores rely on an adaptive cost aggregation step, based on the depth data. Thirdly, the stereo and depth likelihoods are adaptively fused, based on the scene texture and camera geometry. These properties lead to a more selective growing process which, unlike previous seed-growing methods, avoids the tendency to propagate incorrect disparities. The proposed method gives rise to an intrinsically efficient algorithm, which runs at 3FPS on 2.0MP images on a standard desktop computer. The strong performance of the new method is established both by quantitative comparisons with state-of-the-art methods, and by qualitative comparisons using real depth-stereo data-sets [23] . This work is funded by the ANR project MIXCAM.

Website:

https://team.inria.fr/perception/research/dsfusion/

Figure 7. The pipeline of the proposed depth-stereo fusion method [23] . The low-resolution (LR) depth data are projected onto the color data and refined to yield a high-resolution (HR) sparse disparity map. Starting from these disparity seeds, an upsampling process provides an initial HR dense disparity map. Both the HR seeds and the initial dense disparity map are then used by the region-growing depth-stereo fusion to produce the final HR depth map. A prominent feature of our method is that fusion takes place at several data processing stages.