TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
This addresses the problem of efficient and accurate 3D reconstruction from video for applications like robotics or AR/VR, representing an incremental improvement over existing fusion techniques.
The paper tackles 3D scene reconstruction from monocular RGB video by introducing TransformerFusion, a transformer-based method that fuses video frames into a volumetric feature grid and decodes it into an implicit 3D representation, outperforming state-of-the-art methods in accuracy.
We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network that fuses the observations into a volumetric feature grid representing the scene; this feature grid is then decoded into an implicit 3D scene representation. Key to our approach is the transformer architecture that enables the network to learn to attend to the most relevant image frames for each 3D location in the scene, supervised only by the scene reconstruction task. Features are fused in a coarse-to-fine fashion, storing fine-level features only where needed, requiring lower memory storage and enabling fusion at interactive rates. The feature grid is then decoded to a higher-resolution scene reconstruction, using an MLP-based surface occupancy prediction from interpolated coarse-to-fine 3D features. Our approach results in an accurate surface reconstruction, outperforming state-of-the-art multi-view stereo depth estimation methods, fully-convolutional 3D reconstruction approaches, and approaches using LSTM- or GRU-based recurrent networks for video sequence fusion.