view post Post 742 Introducing StereoSpace -- our new end-to-end method for turning photos into stereo images without explicit geometry or depth maps. This makes it especially robust with thin structures and transparencies. Try the demo below:π Project: prs-eth/stereospace_webπ Paper: StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space (2512.10959)π Code: https://github.com/prs-eth/stereospaceπ€ Demo: toshas/stereospaceπ€ Weights: prs-eth/stereospace-v1-0By ETH ZΓΌrich ( @behretj , @Bingxin , @konradschindler ), University of Bologna ( @fabiotosi92 , @mpoggi ), HUAWEI Bayer Lab ( @toshas ). See translation π 3 3 + Reply
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space Paper β’ 2512.10959 β’ Published 15 days ago β’ 12
Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs Paper β’ 2411.19162 β’ Published Nov 28, 2024
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space Paper β’ 2512.10959 β’ Published 15 days ago β’ 12