The development of sophisticated models for video-to-video synthesis has been facilitated by recent advances in deep reinforcement learning and generative adversarial networks (GANs). In this paper, we propose RL-V2V-GAN, a new deep neural network approach based on reinforcement learning for unsupervised conditional video-to-video synthesis. While preserving the unique style of the source video domain, our approach aims to learn a mapping from a source video domain to a target video domain. We train the model using policy gradient and employ ConvLSTM layers to capture the spatial and temporal information by designing a fine-grained GAN architecture and incorporating spatio-temporal adversarial goals. The adversarial losses aid in content translation while preserving style. Unlike traditional video-to-video synthesis methods requiring paired inputs, our proposed approach is more general because it does not require paired inputs. Thus, when dealing with limited videos in the target domain, i.e., few-shot learning, it is particularly effective. Our experiments show that RL-V2V-GAN can produce temporally coherent video results. These results highlight the potential of our approach for further advances in video-to-video synthesis.
Video-to-video synthesis poses significant challenges in maintaining character consistency, smooth temporal transitions, and preserving visual quality during fast motion. While recent fully cross-frame self-attention mechanisms have improved character consistency across multiple frames, they come with high computational costs and often include redundant operations, especially for videos with higher frame rates. To address these inefficiencies, we propose an adaptive motion-guided cross-frame attention mechanism that selectively reduces redundant computations. This enables a greater number of cross-frame attentions over more frames within the same computational budget, thereby enhancing both video quality and temporal coherence. Our method leverages optical flow to focus on moving regions while sparsely attending to stationary areas, allowing for the joint editing of more frames without increasing computational demands. Traditional frame interpolation techniques struggle with motion blur and flickering in intermediate frames, which compromises visual fidelity. To mitigate this, we introduce KV-caching for jointly edited frames, reusing keys and values across intermediate frames to preserve visual quality and maintain temporal consistency throughout the video. With our adaptive cross-frame self-attention approach, we achieve a threefold increase in the number of keyframes processed compared to existing methods, all within the same computational budget as fully cross-frame attention baselines. This results in significant improvements in prediction accuracy and temporal consistency, outperforming state-of-the-art approaches. Code will be made publicly available at https://github.com/tanvir-utexas/AdaVE/tree/main
Translation-based Video Synthesis (TVS) has emerged as a vital research area in computer vision, aiming to facilitate the transformation of videos between distinct domains while preserving both temporal continuity and underlying content features. This technique has found wide-ranging applications, encompassing video super-resolution, colorization, segmentation, and more, by extending the capabilities of traditional image-to-image translation to the temporal domain. One of the principal challenges faced in TVS is the inherent risk of introducing flickering artifacts and inconsistencies between frames during the synthesis process. This is particularly challenging due to the necessity of ensuring smooth and coherent transitions between video frames. Efforts to tackle this challenge have induced the creation of diverse strategies and algorithms aimed at mitigating these unwanted consequences. This comprehensive review extensively examines the latest progress in the realm of TVS. It thoroughly investigates emerging methodologies, shedding light on the fundamental concepts and mechanisms utilized for proficient video synthesis. This survey also illuminates their inherent strengths, limitations, appropriate applications, and potential avenues for future development.
Style transfer is a promising approach to close the sim-to-real gap in medical endoscopy. Rendering synthetic endoscopic videos by traversing pre-operative scans (such as MRI or CT) can generate structurally accurate simulations as well as ground truth camera poses and depth maps. Although image-to-image (I2I) translation models such as CycleGAN can imitate realistic endoscopic images from these simulations, they are unsuitable for video-to-video synthesis due to the lack of temporal consistency, resulting in artifacts between frames. We propose MeshBrush, a neural mesh stylization method to synthesize temporally consistent videos with differentiable rendering. MeshBrush uses the underlying geometry of patient imaging data while leveraging existing I2I methods. With learned per-vertex textures, the stylized mesh guarantees consistency while producing high-fidelity outputs. We demonstrate that mesh stylization is a promising approach for creating realistic simulations for downstream tasks such as training networks and preoperative planning. Although our method is tested and designed for ureteroscopy, its components are transferable to general endoscopic and laparoscopic procedures. The code will be made public on GitHub.
Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of video-to-video (V2V) synthesis has been hampered by the challenge of maintaining temporal consistency across video frames. This paper proposes a consistent V2V synthesis framework by jointly leveraging spatial conditions and temporal optical flow clues within the source video. Contrary to prior methods that strictly adhere to optical flow, our approach harnesses its benefits while handling the imperfection in flow estimation. We encode the optical flow via warping from the first frame and serve it as a supplementary reference in the diffusion model. This enables our model for video synthesis by editing the first frame with any prevalent I2I models and then propagating edits to successive frames. Our V2V model, FlowVid, demonstrates remarkable properties: (1) Flexibility: FlowVid works seamlessly with existing I2I models, facilitating various modifications, including stylization, object swaps, and local edits. (2) Efficiency: Generation of a 4-second video with 30 FPS and 512x512 resolution takes only 1.5 minutes, which is 3.1x, 7.2x, and 10.5x faster than CoDeF, Rerender, and TokenFlow, respectively. (3) High-quality: In user studies, our FlowVid is preferred 45.7% of the time, outperforming CoDeF (3.5%), Rerender (10.2%), and TokenFlow (40.4%).
In this paper, we introduce Fairy, a minimalist yet robust adaptation of image-editing diffusion models, enhancing them for video editing applications. Our approach centers on the concept of anchor-based cross-frame attention, a mechanism that implicitly propagates diffusion features across frames, ensuring superior temporal coherence and high-fidelity synthesis. Fairy not only addresses limitations of previous models, including memory and processing speed. It also improves temporal consistency through a unique data augmentation strategy. This strategy renders the model equivariant to affine transformations in both source and target images. Remarkably efficient, Fairy generates 120-frame 512x384 videos (4-second duration at 30 FPS) in just 14 seconds, outpacing prior works by at least 44x. A comprehensive user study, involving 1000 generated samples, confirms that our approach delivers superior quality, decisively outperforming established methods.
2D animation is a common factor in game development, used for characters, effects and background art. It involves work that takes both skill and time, but parts of which are repetitive and tedious. Automated animation approaches exist, but are designed without animators in mind. The focus is heavily on real-life video, which follows strict laws of how objects move, and does not account for the stylistic movement often present in 2D animation. We propose a problem formulation that more closely adheres to the standard workflow of animation. We also demonstrate a model, SketchBetween, which learns to map between keyframes and sketched in-betweens to rendered sprite animations. We demonstrate that our problem formulation provides the required information for the task and that our model outperforms an existing method.
Video-to-Video synthesis (Vid2Vid) has achieved remarkable results in generating a photo-realistic video from a sequence of semantic maps. However, this pipeline suffers from high computational cost and long inference latency, which largely depends on two essential factors: 1) network architecture parameters, 2) sequential data stream. Recently, the parameters of image-based generative models have been significantly compressed via more efficient network architectures. Nevertheless, existing methods mainly focus on slimming network architectures and ignore the size of the sequential data stream. Moreover, due to the lack of temporal coherence, image-based compression is not sufficient for the compression of the video task. In this paper, we present a spatial-temporal compression framework, \textbf{Fast-Vid2Vid}, which focuses on data aspects of generative models. It makes the first attempt at time dimension to reduce computational resources and accelerate inference. Specifically, we compress the input data stream spatially and reduce the temporal redundancy. After the proposed spatial-temporal knowledge distillation, our model can synthesize key-frames using the low-resolution data stream. Finally, Fast-Vid2Vid interpolates intermediate frames by motion compensation with slight latency. On standard benchmarks, Fast-Vid2Vid achieves around real-time performance as 20 FPS and saves around 8x computational cost on a single V100 GPU.
Untrimmed videos on social media or those captured by robots and surveillance cameras are of varied aspect ratios. However, 3D CNNs usually require as input a square-shaped video, whose spatial dimension is smaller than the original. Random- or center-cropping may leave out the video's subject altogether. To address this, we propose an unsupervised video cropping approach by shaping this as a retargeting and video-to-video synthesis problem. The synthesized video maintains a 1:1 aspect ratio, is smaller in size and is targeted at video-subject(s) throughout the entire duration. First, action localization is performed on each frame by identifying patches with homogeneous motion patterns. Thus, a single salient patch is pinpointed per frame. But to avoid viewpoint jitters and flickering, any inter-frame scale or position changes among the patches should be performed gradually over time. This issue is addressed with a polyBezier fitting in 3D space that passes through some chosen pivot timestamps and whose shape is influenced by the in-between control timestamps. To corroborate the effectiveness of the proposed method, we evaluate the video classification task by comparing our dynamic cropping technique with random cropping on three benchmark datasets, viz. UCF-101, HMDB-51 and ActivityNet v1.3. The clip and top-1 accuracy for video classification after our cropping, outperform 3D CNN performances for same-sized random-crop inputs, also surpassing some larger random-crop sizes.
Video-to-video synthesis (vid2vid) aims for converting high-level semantic inputs to photorealistic videos. While existing vid2vid methods can achieve short-term temporal consistency, they fail to ensure the long-term one. This is because they lack knowledge of the 3D world being rendered and generate each frame only based on the past few frames. To address the limitation, we introduce a novel vid2vid framework that efficiently and effectively utilizes all past generated frames during rendering. This is achieved by condensing the 3D world rendered so far into a physically-grounded estimate of the current frame, which we call the guidance image. We further propose a novel neural network architecture to take advantage of the information stored in the guidance images. Extensive experimental results on several challenging datasets verify the effectiveness of our approach in achieving world consistency - the output video is consistent within the entire rendered 3D world. https://nvlabs.github.io/wc-vid2vid/
Videos of actions are complex signals containing rich compositional structure in space and time. Current video generation methods lack the ability to condition the generation on multiple coordinated and potentially simultaneous timed actions. To address this challenge, we propose to represent the actions in a graph structure called Action Graph and present the new ``Action Graph To Video'' synthesis task. Our generative model for this task (AG2Vid) disentangles motion and appearance features, and by incorporating a scheduling mechanism for actions facilitates a timely and coordinated video generation. We train and evaluate AG2Vid on the CATER and Something-Something V2 datasets, and show that the resulting videos have better visual quality and semantic consistency compared to baselines. Finally, our model demonstrates zero-shot abilities by synthesizing novel compositions of the learned actions. For code and pretrained models, see the project page https://roeiherz.github.io/AG2Video
Video-to-video synthesis is a challenging problem aiming at learning a translation function between a sequence of semantic maps and a photo-realistic video depicting the characteristics of a driving video. We propose a head-to-head system of our own implementation capable of fully transferring the human head 3D pose, facial expressions and eye gaze from a source to a target actor, while preserving the identity of the target actor. Our system produces high-fidelity, temporally-smooth and photo-realistic synthetic videos faithfully transferring the human time-varying head attributes from the source to the target actor. Our proposed implementation: 1) works in real time ($\sim 20$ fps), 2) runs on a commodity laptop with a webcam as the only input, 3) is interactive, allowing the participant to drive a target person, e.g. a celebrity, politician, etc, instantly by varying their expressions, head pose, and eye gaze, and visualising the synthesised video concurrently.
Video-to-video synthesis (vid2vid) aims at converting an input semantic video, such as videos of human poses or segmentation masks, to an output photorealistic video. While the state-of-the-art of vid2vid has advanced significantly, existing approaches share two major limitations. First, they are data-hungry. Numerous images of a target human subject or a scene are required for training. Second, a learned model has limited generalization capability. A pose-to-human vid2vid model can only synthesize poses of the single person in the training set. It does not generalize to other humans that are not in the training set. To address the limitations, we propose a few-shot vid2vid framework, which learns to synthesize videos of previously unseen subjects or scenes by leveraging few example images of the target at test time. Our model achieves this few-shot generalization capability via a novel network weight generation module utilizing an attention mechanism. We conduct extensive experimental validations with comparisons to strong baselines using several large-scale video datasets including human-dancing videos, talking-head videos, and street-scene videos. The experimental results verify the effectiveness of the proposed framework in addressing the two limitations of existing vid2vid approaches.
Blind video decaptioning is a problem of automatically removing text overlays and inpainting the occluded parts in videos without any input masks. While recent deep learning based inpainting methods deal with a single image and mostly assume that the positions of the corrupted pixels are known, we aim at automatic text removal in video sequences without mask information. In this paper, we propose a simple yet effective framework for fast blind video decaptioning. We construct an encoder-decoder model, where the encoder takes multiple source frames that can provide visible pixels revealed from the scene dynamics. These hints are aggregated and fed into the decoder. We apply a residual connection from the input frame to the decoder output to enforce our network to focus on the corrupted regions only. Our proposed model was ranked in the first place in the ECCV Chalearn 2018 LAP Inpainting Competition Track2: Video decaptioning. In addition, we further improve this strong model by applying a recurrent feedback. The recurrent feedback not only enforces temporal coherence but also provides strong clues on where the corrupted pixels are. Both qualitative and quantitative experiments demonstrate that our full model produces accurate and temporally consistent video results in real time (50+ fps).
Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging to extend these methods to the video domain due to the additional time dimension. In this work, we propose a novel deep network architecture for fast video inpainting. Built upon an image-based encoder-decoder model, our framework is designed to collect and refine information from neighbor frames and synthesize still-unknown regions. At the same time, the output is enforced to be temporally consistent by a recurrent feedback and a temporal memory module. Compared with the state-of-the-art image inpainting algorithm, our method produces videos that are much more semantically correct and temporally smooth. In contrast to the prior video completion method which relies on time-consuming optimization, our method runs in near real-time while generating competitive video results. Finally, we applied our framework to video retargeting task, and obtain visually pleasing results.
We study the problem of video-to-video synthesis, whose goal is to learn a mapping function from an input source video (e.g., a sequence of semantic segmentation masks) to an output photorealistic video that precisely depicts the content of the source video. While its image counterpart, the image-to-image synthesis problem, is a popular topic, the video-to-video synthesis problem is less explored in the literature. Without understanding temporal dynamics, directly applying existing image synthesis approaches to an input video often results in temporally incoherent videos of low visual quality. In this paper, we propose a novel video-to-video synthesis approach under the generative adversarial learning framework. Through carefully-designed generator and discriminator architectures, coupled with a spatio-temporal adversarial objective, we achieve high-resolution, photorealistic, temporally coherent video results on a diverse set of input formats including segmentation masks, sketches, and poses. Experiments on multiple benchmarks show the advantage of our method compared to strong baselines. In particular, our model is capable of synthesizing 2K resolution videos of street scenes up to 30 seconds long, which significantly advances the state-of-the-art of video synthesis. Finally, we apply our approach to future video prediction, outperforming several state-of-the-art competing systems.