MonoScene: Monocular 3D Semantic Scene Completion

Abstract

MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense geometry and semantics of a scene are inferred from a single monocular RGB image. Different from the SSC literature, relying on 2.5 or 3D input, we solve the complex problem of 2D to 3D scene reconstruction while jointly inferring its semantics. Our framework relies on successive 2D and 3D UNets bridged by a novel 2D-3D features projection inspiring from optics and introduces a 3D context relation prior to enforce spatio-semantic consistency. Along with architectural contributions, we introduce novel global scene and local frustums losses. Experiments show we outperform the literature on all metrics and datasets while hallucinating plausible scenery even beyond the camera field of view. Our code and trained models are available at https://github.com/cv-rits/MonoScene

Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space

“…Consequently, other studies have focused on learning 3D perception of the input visual signal in order to generalize the learned representation to novel viewpoints. This is done by imposing explicit geometric transform operations in CNNs [3,25,37,41,56], without the requirement of any 3D supervision. In contrast to these existing works, our Transformer-based 3DTRL imposes geometric transformations on visual tokens to recover their representation in a 3D space.…”