Video frame interpolation, the task of synthesizing new frames in between two or more given ones, is becoming an increasingly popular research target. However, the current evaluation of frame interpolation techniques is not ideal. Due to the plethora of test datasets available and inconsistent computation of error metrics, a coherent and fair comparison across papers is very challenging. Furthermore, new test sets have been proposed as part of method papers so they are unable to provide the in-depth evaluation of a dedicated benchmarking paper. Another severe downside is that these test sets violate the assumption of linearity when given two input frames, making it impossible to solve without an oracle. We hence strongly believe that the community would greatly benefit from a benchmarking paper, which is what we propose. Specifically, we present a benchmark which establishes consistent error metrics by utilizing a submission website that computes them, provides insights by analyzing the interpolation quality with respect to various per-pixel attributes such as the motion magnitude, contains a carefully designed test set adhering to the assumption of linearity by utilizing synthetic data, and evaluates the computational efficiency in a coherent manner.
Video frame interpolation methodologies endeavor to create novel frames betwixt extant ones, with the intent of augmenting the video's frame frequency. However, current methods are prone to image blurring and spurious artifacts in challenging scenarios involving occlusions and discontinuous motion. Moreover, they typically rely on optical flow estimation, which adds complexity to modeling and computational costs. To address these issues, we introduce a Motion-Aware Video Frame Interpolation (MA-VFI) network, which directly estimates intermediate optical flow from consecutive frames by introducing a novel hierarchical pyramid module. It not only extracts global semantic relationships and spatial details from input frames with different receptive fields, enabling the model to capture intricate motion patterns, but also effectively reduces the required computational cost and complexity. Subsequently, a cross-scale motion structure is presented to estimate and refine intermediate flow maps by the extracted features. This approach facilitates the interplay between input frame features and flow maps during the frame interpolation process and markedly heightens the precision of the intervening flow delineations. Finally, a discerningly fashioned loss centered around an intermediate flow is meticulously contrived, serving as a deft rudder to skillfully guide the prognostication of said intermediate flow, thereby substantially refining the precision of the intervening flow mappings. Experiments illustrate that MA-VFI surpasses several representative VFI methods across various datasets, and can enhance efficiency while maintaining commendable efficacy.
The quality of frames is significant for both research and application of video frame interpolation (VFI). In recent VFI studies, the methods of full-reference image quality assessment have generally been used to evaluate the quality of VFI frames. However, high frame rate reference videos, necessities for the full-reference methods, are difficult to obtain in most applications of VFI. To evaluate the quality of VFI frames without reference videos, a no-reference perceptual quality assessment method is proposed in this paper. This method is more compatible with VFI application and the evaluation scores from it are consistent with human subjective opinions. A new quality assessment dataset for VFI was constructed through subjective experiments firstly, to assess the opinion scores of interpolated frames. The dataset was created from triplets of frames extracted from high-quality videos using 9 state-of-the-art VFI algorithms. The proposed method evaluates the perceptual coherence of frames incorporating the original pair of VFI inputs. Specifically, the method applies a triplet network architecture, including three parallel feature pipelines, to extract the deep perceptual features of the interpolated frame as well as the original pair of frames. Coherence similarities of the two-way parallel features are jointly calculated and optimized as a perceptual metric. In the experiments, both full-reference and no-reference quality assessment methods were tested on the new quality dataset. The results show that the proposed method achieves the best performance among all compared quality assessment methods on the dataset.
In existing Video Frame Interpolation (VFI) approaches, the motion estimation between neighboring frames plays a crucial role. However, the estimation accuracy in existing methods remains a challenge, primarily due to the inherent ambiguity in identifying corresponding areas in adjacent frames for interpolation. Therefore, enhancing accuracy by distinguishing different regions before motion estimation is of utmost importance. In this paper, we introduce a novel solution involving the utilization of open-world segmentation models, e.g., SAM (Segment Anything Model), to derive Region-Distinguishable Priors (RDPs) in different frames. These RDPs are represented as spatial-varying Gaussian mixtures, distinguishing an arbitrary number of areas with a unified modality. RDPs can be integrated into existing motion-based VFI methods to enhance features for motion estimation, facilitated by our designed play-and-plug Hierarchical Region-aware Feature Fusion Module (HRFFM). HRFFM incorporates RDP into various hierarchical stages of VFI's encoder, using RDP-guided Feature Normalization (RDPFN) in a residual learning manner. With HRFFM and RDP, the features within VFI's encoder exhibit similar representations for matched regions in neighboring frames, thus improving the synthesis of intermediate frames. Extensive experiments demonstrate that HRFFM consistently enhances VFI performance across various scenes.
In general, deep learning-based video frame interpolation (VFI) methods have predominantly focused on estimating motion vectors between two input frames and warping them to the target time. While this approach has shown impressive performance for linear motion between two input frames, it exhibits limitations when dealing with occlusions and nonlinear movements. Recently, generative models have been applied to VFI to address these issues. However, as VFI is not a task focused on generating plausible images, but rather on predicting accurate intermediate frames between two given frames, performance limitations still persist. In this paper, we propose a multi-in-single-out (MISO) based VFI method that does not rely on motion vector estimation, allowing it to effectively model occlusions and nonlinear motion. Additionally, we introduce a novel motion perceptual loss that enables MISO-VFI to better capture the spatio-temporal correlations within the video frames. Our MISO-VFI method achieves state-of-the-art results on VFI benchmarks Vimeo90K, Middlebury, and UCF101, with a significant performance gap compared to existing approaches.
Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movements. Given two images of a baseball, there are infinitely many possible trajectories: accelerating or decelerating, straight or curved. This often results in blurry frames as the method averages out these possibilities. Instead of forcing the network to learn this complicated time-to-location mapping implicitly together with predicting the frames, we provide the network with an explicit hint on how far the object has traveled between start and end frames, a novel approach termed "distance indexing". This method offers a clearer learning goal for models, reducing the uncertainty tied to object speeds. We further observed that, even with this extra guidance, objects can still be blurry especially when they are equally far from both input frames (i.e., halfway in-between), due to the directional ambiguity in long-range motion. To solve this, we propose an iterative reference-based estimation strategy that breaks down a long-range prediction into several short-range steps. When integrating our plug-and-play strategies into state-of-the-art learning-based models, they exhibit markedly sharper outputs and superior perceptual quality in arbitrary time interpolations, using a uniform distance indexing map in the same format as time indexing. Additionally, distance indexing can be specified pixel-wise, which enables temporal manipulation of each object independently, offering a novel tool for video editing tasks like re-timing. The code is available at https://zzh-tech.github.io/InterpAny-Clearer/
In this work, we first propose a fully differentiable Many-to-Many (M2M) splatting framework to interpolate frames efficiently. Given a frame pair, we estimate multiple bidirectional flows to directly forward warp the pixels to the desired time step before fusing overlapping pixels. In doing so, each source pixel renders multiple target pixels and each target pixel can be synthesized from a larger area of visual context, establishing a many-to-many splatting scheme with robustness to undesirable artifacts. For each input frame pair, M2M has a minuscule computational overhead when interpolating an arbitrary number of in-between frames, hence achieving fast multi-frame interpolation. However, directly warping and fusing pixels in the intensity domain is sensitive to the quality of motion estimation and may suffer from less effective representation capacity. To improve interpolation accuracy, we further extend an M2M++ framework by introducing a flexible Spatial Selective Refinement (SSR) component, which allows for trading computational efficiency for interpolation quality and vice versa. Instead of refining the entire interpolated frame, SSR only processes difficult regions selected under the guidance of an estimated error map, thereby avoiding redundant computation. Evaluation on multiple benchmark datasets shows that our method is able to improve the efficiency while maintaining competitive video interpolation quality, and it can be adjusted to use more or less compute as needed.
The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolution (VSR). However, facing the challenge of the additional temporal dimension and scale inconsistency, most existing STVSR methods are complex and inflexible in dynamically modeling different motion amplitudes. In this work, we find that choosing an appropriate processing scale achieves remarkable benefits in flow-based feature propagation. We propose a novel Scale-Adaptive Feature Aggregation (SAFA) network that adaptively selects sub-networks with different processing scales for individual samples. Experiments on four public STVSR benchmarks demonstrate that SAFA achieves state-of-the-art performance. Our SAFA network outperforms recent state-of-the-art methods such as TMNet and VideoINR by an average improvement of over 0.5dB on PSNR, while requiring less than half the number of parameters and only 1/3 computational costs.
Leveraging pre-trained conditional diffusion models for video editing without further tuning has gained increasing attention due to its promise in film production, advertising, etc. Yet, seminal works in this line fall short in generation length, temporal coherence, or fidelity to the source video. This paper aims to bridge the gap, establishing a simple and effective baseline for training-free diffusion model-based long video editing. As suggested by prior arts, we build the pipeline upon ControlNet, which excels at various image editing tasks based on text prompts. To break down the length constraints caused by limited computational memory, we split the long video into consecutive windows and develop a novel cross-window attention mechanism to ensure the consistency of global style and maximize the smoothness among windows. To achieve more accurate control, we extract the information from the source video via DDIM inversion and integrate the outcomes into the latent states of the generations. We also incorporate a video frame interpolation model to mitigate the frame-level flickering issue. Extensive empirical studies verify the superior efficacy of our method over competing baselines across scenarios, including the replacement of the attributes of foreground objects, style transfer, and background replacement. Besides, our method manages to edit videos comprising hundreds of frames according to user requirements. Our project is open-sourced and the project page is at https://github.com/zhijie-group/LOVECon.
Blurry video frame interpolation (BVFI) aims to generate high-frame-rate clear videos from low-frame-rate blurry videos, is a challenging but important topic in the computer vision community. Blurry videos not only provide spatial and temporal information like clear videos, but also contain additional motion information hidden in each blurry frame. However, existing BVFI methods usually fail to fully leverage all valuable information, which ultimately hinders their performance. In this paper, we propose a simple end-to-end three-stage framework to fully explore useful information from blurry videos. The frame interpolation stage designs a temporal deformable network to directly sample useful information from blurry inputs and synthesize an intermediate frame at an arbitrary time interval. The temporal feature fusion stage explores the long-term temporal information for each target frame through a bi-directional recurrent deformable alignment network. And the deblurring stage applies a transformer-empowered Taylor approximation network to recursively recover the high-frequency details. The proposed three-stage framework has clear task assignment for each module and offers good expandability, the effectiveness of which are demonstrated by various experimental results. We evaluate our model on four benchmarks, including the Adobe240 dataset, GoPro dataset, YouTube240 dataset and Sony dataset. Quantitative and qualitative results indicate that our model outperforms existing SOTA methods. Besides, experiments on real-world blurry videos also indicate the good generalization ability of our model.
Learned B-frame video compression aims to adopt bi-directional motion estimation and motion compensation (MEMC) coding for middle frame reconstruction. However, previous learned approaches often directly extend neural P-frame codecs to B-frame relying on bi-directional optical-flow estimation or video frame interpolation. They suffer from inaccurate quantized motions and inefficient motion compensation. To address these issues, we propose a simple yet effective structure called Interpolation-driven B-frame Video Compression (IBVC). Our approach only involves two major operations: video frame interpolation and artifact reduction compression. IBVC introduces a bit-rate free MEMC based on interpolation, which avoids optical-flow quantization and additional compression distortions. Later, to reduce duplicate bit-rate consumption and focus on unaligned artifacts, a residual guided masking encoder is deployed to adaptively select the meaningful contexts with interpolated multi-scale dependencies. In addition, a conditional spatio-temporal decoder is proposed to eliminate location errors and artifacts instead of using MEMC coding in other methods. The experimental results on B-frame coding demonstrate that IBVC has significant improvements compared to the relevant state-of-the-art methods. Meanwhile, our approach can save bit rates compared with the random access (RA) configuration of H.266 (VTM). The code will be available at https://github.com/ruhig6/IBVC.
Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. However, the spatial redundancy when synthesizing the target frame has not been fully explored, that can result in lots of inefficient computation. On the other hand, the computation compression degree in frame interpolation is highly dependent on both texture distribution and scene motion, which demands to understand the spatial-temporal information of each input frame pair for a better compression degree selection. In this work, we propose a novel two-stage frame interpolation framework termed WaveletVFI to address above problems. It first estimates intermediate optical flow with a lightweight motion perception network, and then a wavelet synthesis network uses flow aligned context features to predict multi-scale wavelet coefficients with sparse convolution for efficient target frame reconstruction, where the sparse valid masks that control computation in each scale are determined by a crucial threshold ratio. Instead of setting a fixed value like previous methods, we find that embedding a classifier in the motion perception network to learn a dynamic threshold for each sample can achieve more computation reduction with almost no loss of accuracy. On the common high resolution and animation frame interpolation benchmarks, proposed WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts. Code is available at https://github.com/ltkong218/WaveletVFI.
Human-centric video frame interpolation has great potential for improving people's entertainment experiences and finding commercial applications in the sports analysis industry, e.g., synthesizing slow-motion videos. Although there are multiple benchmark datasets available in the community, none of them is dedicated for human-centric scenarios. To bridge this gap, we introduce SportsSloMo, a benchmark consisting of more than 130K video clips and 1M video frames of high-resolution ($\geq$720p) slow-motion sports videos crawled from YouTube. We re-train several state-of-the-art methods on our benchmark, and the results show a decrease in their accuracy compared to other datasets. It highlights the difficulty of our benchmark and suggests that it poses significant challenges even for the best-performing methods, as human bodies are highly deformable and occlusions are frequent in sports videos. To improve the accuracy, we introduce two loss terms considering the human-aware priors, where we add auxiliary supervision to panoptic segmentation and human keypoints detection, respectively. The loss terms are model agnostic and can be easily plugged into any video frame interpolation approaches. Experimental results validate the effectiveness of our proposed loss terms, leading to consistent performance improvement over 5 existing models, which establish strong baseline models on our benchmark. The dataset and code can be found at: https://neu-vi.github.io/SportsSlomo/.
The video frame interpolation (VFI) model applies the convolution operation to all locations, leading to redundant computations in regions with easy motion. We can use dynamic spatial pruning method to skip redundant computation, but this method cannot properly identify easy regions in VFI tasks without supervision. In this paper, we develop an Uncertainty-Guided Spatial Pruning (UGSP) architecture to skip redundant computation for efficient frame interpolation dynamically. Specifically, pixels with low uncertainty indicate easy regions, where the calculation can be reduced without bringing undesirable visual results. Therefore, we utilize uncertainty-generated mask labels to guide our UGSP in properly locating the easy region. Furthermore, we propose a self-contrast training strategy that leverages an auxiliary non-pruning branch to improve the performance of our UGSP. Extensive experiments show that UGSP maintains performance but reduces FLOPs by 34%/52%/30% compared to baseline without pruning on Vimeo90K/UCF101/MiddleBury datasets. In addition, our method achieves state-of-the-art performance with lower FLOPs on multiple benchmarks.
Video frame interpolation has been actively studied with the development of convolutional neural networks. However, due to the intrinsic limitations of kernel weight sharing in convolution, the interpolated frame generated by it may lose details. In contrast, the attention mechanism in Transformer can better distinguish the contribution of each pixel, and it can also capture long-range pixel dependencies, which provides great potential for video interpolation. Nevertheless, the original Transformer is commonly used for 2D images; how to develop a Transformer-based framework with consideration of temporal self-attention for video frame interpolation remains an open issue. In this paper, we propose Video Frame Interpolation Flow Transformer to incorporate motion dynamics from optical flows into the self-attention mechanism. Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity. In addition, we construct a multi-scale architecture to account for multi-scale motion, further improving the overall performance. Extensive experiments on three benchmarks demonstrate that the proposed method can generate interpolated frames with better visual quality than state-of-the-art methods.
Dynamic vision sensors or event cameras provide rich complementary information for video frame interpolation. Existing state-of-the-art methods follow the paradigm of combining both synthesis-based and warping networks. However, few of those methods fully respect the intrinsic characteristics of events streams. Given that event cameras only encode intensity changes and polarity rather than color intensities, estimating optical flow from events is arguably more difficult than from RGB information. We therefore propose to incorporate RGB information in an event-guided optical flow refinement strategy. Moreover, in light of the quasi-continuous nature of the time signals provided by event cameras, we propose a divide-and-conquer strategy in which event-based intermediate frame synthesis happens incrementally in multiple simplified stages rather than in a single, long stage. Extensive experiments on both synthetic and real-world datasets show that these modifications lead to more reliable and realistic intermediate frame results than previous video frame interpolation methods. Our findings underline that a careful consideration of event characteristics such as high temporal density and elevated noise benefits interpolation accuracy.
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.
Video frame interpolation is an increasingly important research task with several key industrial applications in the video coding, broadcast and production sectors. Recently, transformers have been introduced to the field resulting in substantial performance gains. However, this comes at a cost of greatly increased memory usage, training and inference time. In this paper, a novel method integrating a transformer encoder and convolutional features is proposed. This network reduces the memory burden by close to 50% and runs up to four times faster during inference time compared to existing transformer-based interpolation methods. A dual-encoder architecture is introduced which combines the strength of convolutions in modelling local correlations with those of the transformer for long-range dependencies. Quantitative evaluations are conducted on various benchmarks with complex motion to showcase the robustness of the proposed method, achieving competitive performance compared to state-of-the-art interpolation networks.
We present a neural network architecture designed to naturally learn a positional embedding and overcome the spectral bias towards lower frequencies faced by conventional implicit neural representation networks. Our proposed architecture, SPDER, is a simple MLP that uses an activation function composed of a sinusoidal multiplied by a sublinear function, called the damping function. The sinusoidal enables the network to automatically learn the positional embedding of an input coordinate while the damping passes on the actual coordinate value by preventing it from being projected down to within a finite range of values. Our results indicate that SPDERs speed up training by 10x and converge to losses 1,500-50,000x lower than that of the state-of-the-art for image representation. SPDER is also state-of-the-art in audio representation. The superior representation capability allows SPDER to also excel on multiple downstream tasks such as image super-resolution and video frame interpolation. We provide intuition as to why SPDER significantly improves fitting compared to that of other INR methods while requiring no hyperparameter tuning or preprocessing.
Most consumer cameras use rolling shutter (RS) exposure, which often leads to distortions such as skew and jelly effects. These videos are further limited by bandwidth and frame rate constraints. In this paper, we explore the potential of event cameras, which offer high temporal resolution. We propose a framework to recover global shutter (GS) high-frame-rate videos without RS distortion by combining an RS camera and an event camera. Due to the lack of real-world datasets, our framework adopts a self-supervised strategy based on a displacement field, a dense 3D spatiotemporal representation of pixel motion during exposure. This enables mutual reconstruction between RS and GS frames and facilitates slow-motion recovery. We combine RS frames with the displacement field to generate GS frames, and integrate inverse mapping and RS frame warping for self-supervision. Experiments on four datasets show that our method removes distortion, reduces bandwidth usage by 94 percent, and achieves 16 ms per frame at 32x interpolation.