解决非均匀运动视频插帧模糊问题，提升画面清晰度。
BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions
- 提出双向运动场（BiM）描述非均匀运动轨迹。
- 在LPIPS和STLPIPS上分别提升26%和45%，大幅减少模糊。
- 适合需要高精度运动建模的视频增强场景。
现有视频插帧（VFI）模型在处理非均匀运动（如加速、减速、方向变化）时，常因时间-位置歧义导致插帧模糊。本文提出：(i) 新型运动描述图——双向运动场（BiM），有效刻画非均匀运动；(ii) 基于内容感知上采样的双向运动场引导流网络（BiMFN）以实现精确光流估计；(iii) 面向插帧任务的教师流知识蒸馏（KDVCF），用插帧专用教师流监督运动估计。所提方法称为BiM-VFI。大量实验表明，该模型在LPIPS和STLPIPS指标上分别较最新SOTA提升26%和45%，在任意时间点生成的插帧图像显著更清晰，模糊更少。
原文摘要 · Abstract (English)
Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred interpolated frames. In this paper, we propose (i) a novel motion description map, Bidirectional Motion field (BiM), to effectively describe non-uniform motions; (ii) a BiM-guided Flow Net (BiMFN) with Content-Aware Upsampling Network (CAUN) for precise optical flow estimation; and (iii) Knowledge Distillation for VFI-centric Flow supervision (KDVCF) to supervise the motion estimation of VFI model with VFI-centric teacher flows. The proposed VFI is called a Bidirectional Motion field-guided VFI (BiM-VFI) model. Extensive experiments show that our BiM-VFI model significantly surpasses the recent state-of-the-art VFI methods by 26% and 45% improvements in LPIPS and STLPIPS respectively, yielding interpolated frames with much fewer blurs at arbitrary time instances.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。