Author name: Tjark Behrens, Anton Obukhov, Bingxin Ke, Fabio Tosi, Matteo Poggi, Konrad Schindler

arXiv:2512.10959v3 Announce Type: replace
Abstract: We introduce StereoSpace, a diffusion-based framework for monocular-to-stereo synthesis that models geometry purely through viewpoint conditioning, without explicit depth or warping. A canonical rect…

arXiv:2512.10959v2 Announce Type: replace
Abstract: We introduce StereoSpace, a diffusion-based framework for monocular-to-stereo synthesis that models geometry purely through viewpoint conditioning, without explicit depth or warping. A canonical rect…