From Sim-to-Real: Toward General Event-based Low-light Frame Interpolation with Per-scene Optimization

TL;DR

This paper introduces a novel per-scene optimization method for event-based video frame interpolation in low-light conditions, leveraging internal sequence statistics to improve robustness and generalization, validated on a new low-light dataset.

Contribution

It presents a new per-scene optimization strategy for low-light event-based VFI and introduces EVFI-LL, a dataset for low-light conditions, achieving state-of-the-art results.

Findings

State-of-the-art performance in low-light environments.

Effective handling of degraded event data.

Robust generalization across different lighting conditions.

Abstract

Video Frame Interpolation (VFI) is important for video enhancement, frame rate up-conversion, and slow-motion generation. The introduction of event cameras, which capture per-pixel brightness changes asynchronously, has significantly enhanced VFI capabilities, particularly for high-speed, nonlinear motions. However, these event-based methods encounter challenges in low-light conditions, notably trailing artifacts and signal latency, which hinder their direct applicability and generalization. Addressing these issues, we propose a novel per-scene optimization strategy tailored for low-light conditions. This approach utilizes the internal statistics of a sequence to handle degraded event data under low-light conditions, improving the generalizability to different lighting and camera settings. To evaluate its robustness in low-light condition, we further introduce EVFI-LL, a unique RGB+Event dataset captured under low-light conditions. Our results demonstrate state-of-the-art performance in low-light environments. Project page: https://naturezhanghn.github.io/sim2real.