Cross-View Panorama Image Synthesis

TL;DR

This paper introduces PanoGAN, a novel adversarial feedback GAN framework that synthesizes ground-view panorama images from top-view aerial images, improving detail and semantic consistency through iterative refinement.

Contribution

The paper proposes a new adversarial feedback mechanism and dual branch discrimination strategy for cross-view panorama synthesis, enhancing image quality and semantic accuracy.

Findings

PanoGAN outperforms state-of-the-art methods in detail and realism.

The feedback mechanism improves intermediate feature representations.

The dual discrimination strategy ensures semantic consistency.

Abstract

In this paper, we tackle the problem of synthesizing a ground-view panorama image conditioned on a top-view aerial image, which is a challenging problem due to the large gap between the two image domains with different view-points. Instead of learning cross-view mapping in a feedforward pass, we propose a novel adversarial feedback GAN framework named PanoGAN with two key components: an adversarial feedback module and a dual branch discrimination strategy. First, the aerial image is fed into the generator to produce a target panorama image and its associated segmentation map in favor of model training with layout semantics. Second, the feature responses of the discriminator encoded by our adversarial feedback module are fed back to the generator to refine the intermediate representations, so that the generation performance is continually improved through an iterative generation process. Third, to pursue high-fidelity and semantic consistency of the generated panorama image, we propose a pixel-segmentation alignment mechanism under the dual branch discrimiantion strategy to facilitate cooperation between the generator and the discriminator. Extensive experimental results on two challenging cross-view image datasets show that PanoGAN enables high-quality panorama image generation with more convincing details than state-of-the-art approaches. The source code and trained models are available at \url{https://github.com/sswuai/PanoGAN}.