VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors
This addresses depth estimation for volumetric capture systems, where accurate depth is crucial for reconstruction, though it appears incremental as it builds on existing recurrent network architectures.
The paper tackles high-resolution stereo matching for depth estimation by using visual hull priors from supplementary views to guide disparity estimation, reducing the search space and improving efficiency. It demonstrates competitive performance with state-of-the-art methods while enabling training on high-resolution data through memory-efficient techniques.
We present a stereo-matching method for depth estimation from high-resolution images using visual hulls as priors, and a memory-efficient technique for the correlation computation. Our method uses object masks extracted from supplementary views of the scene to guide the disparity estimation, effectively reducing the search space for matches. This approach is specifically tailored to stereo rigs in volumetric capture systems, where an accurate depth plays a key role in the downstream reconstruction task. To enable training and regression at high resolutions targeted by recent systems, our approach extends a sparse correlation computation into a hybrid sparse-dense scheme suitable for application in leading recurrent network architectures. We evaluate the performance-efficiency trade-off of our method compared to state-of-the-art methods, and demonstrate the efficacy of the visual hull guidance. In addition, we propose a training scheme for a further reduction of memory requirements during optimization, facilitating training on high-resolution data.