CVGRJan 7, 2024

See360: Novel Panoramic View Interpolation

arXiv:2401.03431v15 citationsh-index: 53IEEE Transactions on Image Processing
AI Analysis

This addresses camera-centered view synthesis for panoramic scene exploration, offering a versatile solution for both indoor and outdoor environments, though it appears incremental as it builds on existing view rendering approaches.

The paper tackles 360 panoramic view interpolation by proposing See360, a framework that renders novel views from reference images using a Multi-Scale Affine Transformer and Conditional Latent space AutoEncoder, achieving real-time rendering on four diverse datasets and adapting to unknown scenes with minimal extra training.

We present See360, which is a versatile and efficient framework for 360 panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments and render new views of small objects. In contrast, we suggest to tackle camera-centered view synthesis as a 2D affine transformation without using point clouds or depth maps, which enables an effective 360? panoramic scene exploration. Given a pair of reference images, the See360 model learns to render novel views by a proposed novel Multi-Scale Affine Transformer (MSAT), enabling the coarse-to-fine feature rendering. We also propose a Conditional Latent space AutoEncoder (C-LAE) to achieve view interpolation at any arbitrary angle. To show the versatility of our method, we introduce four training datasets, namely UrbanCity360, Archinterior360, HungHom360 and Lab360, which are collected from indoor and outdoor environments for both real and synthetic rendering. Experimental results show that the proposed method is generic enough to achieve real-time rendering of arbitrary views for all four datasets. In addition, our See360 model can be applied to view synthesis in the wild: with only a short extra training time (approximately 10 mins), and is able to render unknown real-world scenes. The superior performance of See360 opens up a promising direction for camera-centered view rendering and 360 panoramic view interpolation.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes