Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
This addresses the challenge of 3D scene understanding for computer vision applications by enabling unsupervised learning from 2D data, though it builds on existing neural scene representation methods.
The paper tackles the problem of learning 3D scene representations without explicit 3D supervision by proposing Scene Representation Networks (SRNs), which encode geometry and appearance as continuous functions and are trained end-to-end from only 2D images and camera poses, achieving results in tasks like novel view synthesis and few-shot reconstruction.
Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes. While geometric deep learning has explored 3D-structure-aware representations of scene geometry, these models typically require explicit 3D supervision. Emerging neural scene representations can be trained only with posed 2D images, but existing methods ignore the three-dimensional structure of scenes. We propose Scene Representation Networks (SRNs), a continuous, 3D-structure-aware scene representation that encodes both geometry and appearance. SRNs represent scenes as continuous functions that map world coordinates to a feature representation of local scene properties. By formulating the image formation as a differentiable ray-marching algorithm, SRNs can be trained end-to-end from only 2D images and their camera poses, without access to depth or shape. This formulation naturally generalizes across scenes, learning powerful geometry and appearance priors in the process. We demonstrate the potential of SRNs by evaluating them for novel view synthesis, few-shot reconstruction, joint shape and appearance interpolation, and unsupervised discovery of a non-rigid face model.