Video frame interpolation (VFI) has witnessed great progress in recent years. However, existing VFI models still struggle to achieve a good trade-off between accuracy and efficiency. Accurate VFI models typically rely on heavy compute to process all samples, ignoring the fact that easy samples with small motion or clear texture can be well addressed by a fast VFI model and do not require such heavy compute. In this paper, we present a dynamic VFI pipeline with integrated pre-assessment of interpolation difficulty. Specifically, it leverages a difficulty pre-assessment model to measure the difficulty level of interpolating input frames, and then dynamically selects an accurate or a fast VFI model for frame interpolation. Furthermore, we contribute a large-scale annotated dataset to train our VFI difficulty pre-assessment model. Extensive experiments show that our dynamic VFI pipeline can achieve an excellent trade-off between accuracy and efficiency, by feeding hard samples to accurate model, and passing easy samples through fast model.

Flow-guided synthesis provides a common framework for frame interpolation, where optical flow is estimated to guide the synthesis of intermediate frames between consecutive inputs. In this paper, we present UPR-Net, a novel Unified Pyramid Recurrent Network for frame interpolation. Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis. At each pyramid level, it leverages estimated bi-directional flow to generate forward-warped representations for frame synthesis; across pyramid levels, it enables iterative refinement for both optical flow and intermediate frame. In particular, we show that our iterative synthesis strategy can significantly improve the robustness of frame interpolation on large motion cases. Despite being extremely lightweight (1.7M parameters), our base version of UPR-Net achieves excellent performance on a large range of benchmarks. Code and trained models of our UPR-Net series are available at: https://github.com/srcn-iv1/UPR-Net.

No-Reference Image Quality Assessment (NR-IQA) techniques have shown improved performance with the help of deep-learning but lightweight architectures have not received attention. In this paper, we propose an NR-IQA network named Lightweight Non-uniform Weighting-based NR-IQA (LiNuIQA) that adopts an efficient network as a feature extractor for a resource constraint environment and harnesses non-uniformly self-weighted local (from each patch) and global information (from all patches) to overcome the inherent problem of low performance stemming from use of lightweight feature extractor. This non-uniform weighting technique is designed to utilize combinations of local and global information with very low resources unlike conventional weighting techniques. The experimental results show that our network outperforms several recently popular NR-IQA networks in terms of both PLCC and SRCC while having the smallest number of parameters and multiply-adds (MAdd) operations. In addition, it can be seen from our experiments that appropriate weighting method plays an important role in IQA and can be implemented with extremely low resources.

We propose a simple yet effective algorithm for motion-based video frame interpolation. Existing motion-based interpolation methods typically rely on an off-the-shelf optical flow model or a U-Net based pyramid network for motion estimation, which either suffer from large model size or limited capacity in handling various challenging motion cases. In this work, we present a novel compact model to simultaneously estimate the bi-directional motions between input frames. It is designed by carefully adapting the ingredients (e.g., warping, correlation) in optical flow research for simultaneous bi-directional motion estimation within a flexible pyramid recurrent framework. Our motion estimator is extremely lightweight (15x smaller than PWC-Net), yet enables reliable handling of large and complex motion cases. Based on estimated bi-directional motions, we employ a synthesis network to fuse forward-warped representations and predict the intermediate frame. Our method achieves excellent performance on a broad range of frame interpolation benchmarks. Code and trained models are available at https://github.com/srcn-ivl/EBME.