Video Frame Interpolation with Stereo Event and Intensity Camera

TL;DR

This paper introduces SEVFI-Net, a novel stereo event-based video frame interpolation network that effectively handles cross-modality parallax and complex motions, producing high-quality intermediate frames and disparities.

Contribution

The paper proposes a new stereo event-based VFI network with a feature aggregation module and a new stereo dataset, improving interpolation accuracy in challenging real-world scenes.

Findings

SEVFI-Net outperforms existing methods on public datasets.

The feature aggregation module effectively reduces parallax artifacts.

The new dataset captures diverse scenes with complex motions.

Abstract

The stereo event-intensity camera setup is widely applied to leverage the advantages of both event cameras with low latency and intensity cameras that capture accurate brightness and texture information. However, such a setup commonly encounters cross-modality parallax that is difficult to be eliminated solely with stereo rectification especially for real-world scenes with complex motions and varying depths, posing artifacts and distortion for existing Event-based Video Frame Interpolation (E-VFI) approaches. To tackle this problem, we propose a novel Stereo Event-based VFI (SE-VFI) network (SEVFI-Net) to generate high-quality intermediate frames and corresponding disparities from misaligned inputs consisting of two consecutive keyframes and event streams emitted between them. Specifically, we propose a Feature Aggregation Module (FAM) to alleviate the parallax and achieve spatial alignment in the feature domain. We then exploit the fused features accomplishing accurate optical flow and disparity estimation, and achieving better interpolated results through flow-based and synthesis-based ways. We also build a stereo visual acquisition system composed of an event camera and an RGB-D camera to collect a new Stereo Event-Intensity Dataset (SEID) containing diverse scenes with complex motions and varying depths. Experiments on public real-world stereo datasets, i.e., DSEC and MVSEC, and our SEID dataset demonstrate that our proposed SEVFI-Net outperforms state-of-the-art methods by a large margin.