Learning Cross-Video Neural Representations for High-Quality Frame Interpolation
This addresses the problem of generating high-quality intermediate frames in videos for applications like video editing and enhancement, representing an incremental advance by applying neural fields to a new task.
The paper tackles temporal video interpolation by proposing Cross-Video Neural Representation (CURE), the first method based on neural fields, which achieves state-of-the-art performance on multiple benchmark datasets.
This paper considers the problem of temporal video interpolation, where the goal is to synthesize a new video frame given its two neighbors. We propose Cross-Video Neural Representation (CURE) as the first video interpolation method based on neural fields (NF). NF refers to the recent class of methods for the neural representation of complex 3D scenes that has seen widespread success and application across computer vision. CURE represents the video as a continuous function parameterized by a coordinate-based neural network, whose inputs are the spatiotemporal coordinates and outputs are the corresponding RGB values. CURE introduces a new architecture that conditions the neural network on the input frames for imposing space-time consistency in the synthesized video. This not only improves the final interpolation quality, but also enables CURE to learn a prior across multiple videos. Experimental evaluations show that CURE achieves the state-of-the-art performance on video interpolation on several benchmark datasets.