Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data
This could help unlock 3D reconstruction from abundant phone-based accelerometer+RGBD data, though it appears incremental as it builds on existing implicit function approaches.
The paper tackles 3D reconstruction from posed RGBD data by learning scene-level implicit functions, achieving performance that matches or outperforms mesh-supervised methods with better robustness to sparse data.
We introduce a method that can learn to predict scene-level implicit functions for 3D reconstruction from posed RGBD data. At test time, our system maps a previously unseen RGB image to a 3D reconstruction of a scene via implicit functions. While implicit functions for 3D reconstruction have often been tied to meshes, we show that we can train one using only a set of posed RGBD images. This setting may help 3D reconstruction unlock the sea of accelerometer+RGBD data that is coming with new phones. Our system, D2-DRDF, can match and sometimes outperform current methods that use mesh supervision and shows better robustness to sparse data.