Figure 1: The DeepView architecture. (a) The network takes a sparse set of input images shot from different viewpoints. (b, c) The scene is reconstructed using learned gradient descent, producing a multi-plane image (a series of fronto-parallel, RGBA textured planes). (d) The multi-plane image is suitable for real-time, high-quality rendering of novel viewpoints. The result above uses four input views in a 30cm × 20cm rectangular layout. The novel view was rendered with a virtual camera positioned at the centroid of the four input views. More results, including video and an interactive viewer, at: https://augmentedperception.github.io/deepview/ AbstractWe present a novel approach to view synthesis using multiplane images (MPIs). Building on recent advances in learned gradient descent, our algorithm generates an MPI from a set of sparse camera viewpoints. The resulting method incorporates occlusion reasoning, improving performance on challenging scene features such as object boundaries, lighting reflections, thin structures, and scenes with high depth complexity. We show that our method achieves high-quality, state-of-the-art results on two datasets: the Kalantari light field dataset, and a new camera array dataset, Spaces, which we make publicly available.

Train Static scene, moving camera MannequinChallenge (MC) Dataset Predicted depth Human Mask Initial depth from flow RGB Image MVS Depth (supervison) Inference Our depth predictions Moving people, moving camera

No abstract

We present an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but also to capture the texture and depth for content in the scene that is not directly visible. We overcome the challenge posed by the lack of direct supervision by instead leveraging a more naturally available multi-view supervisory signal. Our insight is to use view synthesis as a proxy task: we enforce that our representation (inferred from a single image), when rendered from a novel perspective, matches the true observed image. We present a learning framework that operationalizes this insight using a new, differentiable novel view renderer. We provide qualitative and quantitative validation of our approach in two different settings, and demonstrate that we can learn to capture the hidden aspects of a scene. The project website can be found at https://shubhtuls.github. io/lsi/.