PS4PRO: Pixel-to-pixel Supervision for Photorealistic Rendering and Optimization

TL;DR

This paper introduces PS4PRO, a novel video frame interpolation model that enhances neural rendering by augmenting data, leading to improved 3D scene reconstruction in static and dynamic environments.

Contribution

The paper presents PS4PRO, a lightweight high-quality video interpolation model that implicitly models camera movement and geometry to improve neural rendering and 3D reconstruction.

Findings

Improved reconstruction quality in static scenes.

Enhanced performance in dynamic scenes.

Effective data augmentation for neural rendering.

Abstract

Neural rendering methods have gained significant attention for their ability to reconstruct 3D scenes from 2D images. The core idea is to take multiple views as input and optimize the reconstructed scene by minimizing the uncertainty in geometry and appearance across the views. However, the reconstruction quality is limited by the number of input views. This limitation is further pronounced in complex and dynamic scenes, where certain angles of objects are never seen. In this paper, we propose to use video frame interpolation as the data augmentation method for neural rendering. Furthermore, we design a lightweight yet high-quality video frame interpolation model, PS4PRO (Pixel-to-pixel Supervision for Photorealistic Rendering and Optimization). PS4PRO is trained on diverse video datasets, implicitly modeling camera movement as well as real-world 3D geometry. Our model performs as an implicit world prior, enriching the photo supervision for 3D reconstruction. By leveraging the proposed method, we effectively augment existing datasets for neural rendering methods. Our experimental results indicate that our method improves the reconstruction performance on both static and dynamic scenes.