Stereo Magnification With Multi-Layer Images

Abstract

Representing scenes with multiple semitransparent colored layers has been a popular and successful choice for real-time novel view synthesis. Existing approaches infer colors and transparency values over regularly spaced layers of planar or spherical shape. In this work, we introduce a new view synthesis approach based on multiple semitransparent layers with scene-adapted geometry. Our approach infers such representations from stereo pairs in two stages. The first stage produces the geometry of a small number of data-adaptive layers from a given pair of views. The second stage infers the color and transparency values for these layers, producing the final representation for novel view synthesis. Importantly, both stages are connected through a differentiable renderer and are trained end-to-end. In the experiments, we demonstrate the advantage of the proposed approach over the use of regularly spaced layers without adaptation to scene geometry. Despite being orders of magnitude faster during rendering, our approach also outperforms the recently proposed IBRNet system based on implicit geometry representation.

Citation Style:    Display Alpha ACM SIGGRAPH IEEEtran Publication

Stereo Magnification With Multi-Layer Images. Taras Khakhulin, Denis Korzhenkov, Pavel Solovev, Gleb Sterkin, Andrei-Timotei Ardelean, Victor Lempitsky. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 8687-8696.Taras Khakhulin, Denis Korzhenkov, Pavel Solovev, Gleb Sterkin, Andrei-Timotei Ardelean, and Victor Lempitsky. Stereo magnification with multi-layer images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8687–8696, June 2022.Khakhulin, T., Korzhenkov, D., Solovev, P., Sterkin, G., Ardelean, A.-T., and Lempitsky, V. 2022. Stereo magnification with multi-layer images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8687–8696.T. Khakhulin, D. Korzhenkov, P. Solovev, G. Sterkin, A.-T. Ardelean, and V. Lempitsky, “Stereo magnification with multi-layer images,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2022, pp. 8687–8696. Project Page PDF Supp. Mat. BibTeX

Acknowledgments