PyTorchKR Papers

최신 논문

총 1,879편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2211.13221공식 코드 · Papers with Code

Latent Video Diffusion Models for High-Fidelity Long Video Generation

AI-generated content has attracted lots of attention recently, but photo-realistic video synthesis is still challenging. Although many attempts using GANs and autoregressive models have been made in this area, the visual quality and length of generated videos are far from satisfactory. Diffusion models have shown remarkable results recently but require significant computational resources. To address this, we introduce lightweight video diffusion models by leveraging a low-dimensional 3D latent space, significantly outperforming previous pixel-space video diffusion models under a limited computational budget. In addition, we propose hierarchical diffusion in the latent space such that longer videos with more than one thousand frames can be produced. To further overcome the performance degradation issue for long video generation, we propose conditional latent perturbation and unconditional guidance that effectively mitigate the accumulated errors during the extension of video length. Extensive experiments on small domain datasets of different categories suggest that our framework generates more realistic and longer videos than previous strong baselines. We additionally provide an extension to large-scale text-to-video generation to demonstrate the superiority of our work. Our code and models will be made publicly available.

arXiv:2211.11018

MagicVideo: Efficient Video Generation With Latent Diffusion Models

We present an efficient text-to-video generation framework based on latent diffusion models, termed MagicVideo. MagicVideo can generate smooth video clips that are concordant with the given text descriptions. Due to a novel and efficient 3D U-Net design and modeling video distributions in a low-dimensional space, MagicVideo can synthesize video clips with 256x256 spatial resolution on a single GPU card, which takes around 64x fewer computations than the Video Diffusion Models (VDM) in terms of FLOPs. In specific, unlike existing works that directly train video models in the RGB space, we use a pre-trained VAE to map video clips into a low-dimensional latent space and learn the distribution of videos' latent codes via a diffusion model. Besides, we introduce two new designs to adapt the U-Net denoiser trained on image tasks to video data: a frame-wise lightweight adaptor for the image-to-video distribution adjustment and a directed temporal attention module to capture temporal dependencies across frames. Thus, we can exploit the informative weights of convolution operators from a text-to-image model for accelerating video training. To ameliorate the pixel dithering in the generated videos, we also propose a novel VideoVAE auto-encoder for better RGB reconstruction. We conduct extensive experiments and demonstrate that MagicVideo can generate high-quality video clips with either realistic or imaginary content. Refer to \url{https://magicvideo.github.io/#} for more examples.

arXiv:2211.11743공식 코드 · Papers with Code

SinFusion: Training Diffusion Models on a Single Image or Video

Diffusion models exhibited tremendous progress in image and video generation, exceeding GANs in quality and diversity. However, they are usually trained on very large datasets and are not naturally adapted to manipulate a given input image or video. In this paper we show how this can be resolved by training a diffusion model on a single input image or video. Our image/video-specific diffusion model (SinFusion) learns the appearance and dynamics of the single image or video, while utilizing the conditioning capabilities of diffusion models. It can solve a wide array of image/video-specific manipulation tasks. In particular, our model can learn from few frames the motion and dynamics of a single input video. It can then generate diverse new video samples of the same dynamic scene, extrapolate short videos into long ones (both forward and backward in time) and perform video upsampling. Most of these tasks are not realizable by current video-specific generation methods.

arXiv:2211.04894공식 코드 · Papers with Code

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

The rapid increase in user-generated-content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be viewed from two perspectives: the technical perspective, measuring the perception of distortions; and the aesthetic perspective, which relates to preference and recommendation on contents. To understand how these two perspectives affect overall subjective opinions in UGC-VQA, we conduct a large-scale subjective study to collect human quality opinions on overall quality of videos as well as perceptions from aesthetic and technical perspectives. The collected Disentangled Video Quality Database (DIVIDE-3k) confirms that human quality opinions on UGC videos are universally and inevitably affected by both aesthetic and technical perspectives. In light of this, we propose the Disentangled Objective Video Quality Evaluator (DOVER) to learn the quality of UGC videos based on the two perspectives. The DOVER proves state-of-the-art performance in UGC-VQA under very high efficiency. With perspective opinions in DIVIDE-3k, we further propose DOVER++, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective. Code at https://github.com/VQAssessment/DOVER.

arXiv:2210.16579공식 코드 · Papers with Code

INR-V: A Continuous Representation Space for Video-based Generative Tasks

Generating videos is a complex task that is accomplished by generating a set of temporally coherent images frame-by-frame. This limits the expressivity of videos to only image-based operations on the individual video frames needing network designs to obtain temporally coherent trajectories in the underlying image space. We propose INR-V, a video representation network that learns a continuous space for video-based generative tasks. INR-V parameterizes videos using implicit neural representations (INRs), a multi-layered perceptron that predicts an RGB value for each input pixel location of the video. The INR is predicted using a meta-network which is a hypernetwork trained on neural representations of multiple video instances. Later, the meta-network can be sampled to generate diverse novel videos enabling many downstream video-based generative tasks. Interestingly, we find that conditional regularization and progressive weight initialization play a crucial role in obtaining INR-V. The representation space learned by INR-V is more expressive than an image space showcasing many interesting properties not possible with the existing works. For instance, INR-V can smoothly interpolate intermediate videos between known video instances (such as intermediate identities, expressions, and poses in face videos). It can also in-paint missing portions in videos to recover temporally coherent full videos. In this work, we evaluate the space learned by INR-V on diverse generative tasks such as video interpolation, novel video generation, video inversion, and video inpainting against the existing baselines. INR-V significantly outperforms the baselines on several of these demonstrated tasks, clearly showcasing the potential of the proposed representation space.

arXiv:2210.11182

Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN

Facial expression generation has always been an intriguing task for scientists and researchers all over the globe. In this context, we present our novel approach for generating videos of the six basic facial expressions. Starting from a single neutral facial image and a label indicating the desired facial expression, we aim to synthesize a video of the given identity performing the specified facial expression. Our approach, referred to as FEV-GAN (Facial Expression Video GAN), is based on Spatio-temporal Convolutional GANs, that are known to model both content and motion in the same network. Previous methods based on such a network have shown a good ability to generate coherent videos with smooth temporal evolution. However, they still suffer from low image quality and low identity preservation capability. In this work, we address this problem by using a generator composed of two image encoders. The first one is pre-trained for facial identity feature extraction and the second for spatial feature extraction. We have qualitatively and quantitatively evaluated our model on two international facial expression benchmark databases: MUG and Oulu-CASIA NIR&VIS. The experimental results analysis demonstrates the effectiveness of our approach in generating videos of the six basic facial expressions while preserving the input identity. The analysis also proves that the use of both identity and spatial features enhances the decoder ability to better preserve the identity and generate high-quality videos. The code and the pre-trained model will soon be made publicly available.

arXiv:2210.04429

DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction

Due to hardware constraints, standard off-the-shelf digital cameras suffers from low dynamic range (LDR) and low frame per second (FPS) outputs. Previous works in high dynamic range (HDR) video reconstruction uses sequence of alternating exposure LDR frames as input, and align the neighbouring frames using optical flow based networks. However, these methods often result in motion artifacts in challenging situations. This is because, the alternate exposure frames have to be exposure matched in order to apply alignment using optical flow. Hence, over-saturation and noise in the LDR frames results in inaccurate alignment. To this end, we propose to align the input LDR frames using a pre-trained video frame interpolation network. This results in better alignment of LDR frames, since we circumvent the error-prone exposure matching step, and directly generate intermediate missing frames from the same exposure inputs. Furthermore, it allows us to generate high FPS HDR videos by recursively interpolating the intermediate frames. Through this work, we propose to use video frame interpolation for HDR video reconstruction, and present the first method to generate high FPS HDR videos. Experimental results demonstrate the efficacy of the proposed framework against optical flow based alignment methods, with an absolute improvement of 2.4 PSNR value on standard HDR video datasets [1], [2] and further benchmark our method for high FPS HDR video generation.

arXiv:2210.03825

See, Plan, Predict: Language-guided Cognitive Planning with Video Prediction

Cognitive planning is the structural decomposition of complex tasks into a sequence of future behaviors. In the computational setting, performing cognitive planning entails grounding plans and concepts in one or more modalities in order to leverage them for low level control. Since real-world tasks are often described in natural language, we devise a cognitive planning algorithm via language-guided video prediction. Current video prediction models do not support conditioning on natural language instructions. Therefore, we propose a new video prediction architecture which leverages the power of pre-trained transformers.The network is endowed with the ability to ground concepts based on natural language input with generalization to unseen objects. We demonstrate the effectiveness of this approach on a new simulation dataset, where each task is defined by a high-level action described in natural language. Our experiments compare our method again stone video generation baseline without planning or action grounding and showcase significant improvements. Our ablation studies highlight an improved generalization to unseen objects that natural language embeddings offer to concept grounding ability, as well as the importance of planning towards visual "imagination" of a task.

arXiv:2210.04366공식 코드 · Papers with Code

KP-RNN: A Deep Learning Pipeline for Human Motion Prediction and Synthesis of Performance Art

Digitally synthesizing human motion is an inherently complex process, which can create obstacles in application areas such as virtual reality. We offer a new approach for predicting human motion, KP-RNN, a neural network which can integrate easily with existing image processing and generation pipelines. We utilize a new human motion dataset of performance art, Take The Lead, as well as the motion generation pipeline, the Everybody Dance Now system, to demonstrate the effectiveness of KP-RNN's motion predictions. We have found that our neural network can predict human dance movements effectively, which serves as a baseline result for future works using the Take The Lead dataset. Since KP-RNN can work alongside a system such as Everybody Dance Now, we argue that our approach could inspire new methods for rendering human avatar animation. This work also serves to benefit the visualization of performance art in digital platforms by utilizing accessible neural networks.

arXiv:2210.02872

Text-driven Video Prediction

Current video generation models usually convert signals indicating appearance and motion received from inputs (e.g., image, text) or latent spaces (e.g., noise vectors) into consecutive frames, fulfilling a stochastic generation process for the uncertainty introduced by latent code sampling. However, this generation pattern lacks deterministic constraints for both appearance and motion, leading to uncontrollable and undesirable outcomes. To this end, we propose a new task called Text-driven Video Prediction (TVP). Taking the first frame and text caption as inputs, this task aims to synthesize the following frames. Specifically, appearance and motion components are provided by the image and caption separately. The key to addressing the TVP task depends on fully exploring the underlying motion information in text descriptions, thus facilitating plausible video generation. In fact, this task is intrinsically a cause-and-effect problem, as the text content directly influences the motion changes of frames. To investigate the capability of text in causal inference for progressive motion information, our TVP framework contains a Text Inference Module (TIM), producing step-wise embeddings to regulate motion inference for subsequent frames. In particular, a refinement mechanism incorporating global motion semantics guarantees coherent generation. Extensive experiments are conducted on Something-Something V2 and Single Moving MNIST datasets. Experimental results demonstrate that our model achieves better results over other baselines, verifying the effectiveness of the proposed framework.

arXiv:2210.02399

Phenaki: Variable Length Video Generation From Open Domain Textual Description

We present Phenaki, a model capable of realistic video synthesis, given a sequence of textual prompts. Generating videos from text is particularly challenging due to the computational cost, limited quantities of high quality text-video data and variable length of videos. To address these issues, we introduce a new model for learning video representation which compresses the video to a small representation of discrete tokens. This tokenizer uses causal attention in time, which allows it to work with variable-length videos. To generate video tokens from text we are using a bidirectional masked transformer conditioned on pre-computed text tokens. The generated video tokens are subsequently de-tokenized to create the actual video. To address data issues, we demonstrate how joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets. Compared to the previous video generation methods, Phenaki can generate arbitrary long videos conditioned on a sequence of prompts (i.e. time variable text or a story) in open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts. In addition, compared to the per-frame baselines, the proposed video encoder-decoder computes fewer tokens per video but results in better spatio-temporal consistency.

arXiv:2210.02396공식 코드 · Papers with Code

Temporally Consistent Transformers for Video Generation

To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. Current algorithms enable accurate predictions over short horizons but tend to suffer from temporal inconsistencies. When generated content goes out of view and is later revisited, the model invents different content instead. Despite this severe limitation, no established benchmarks on complex data exist for rigorously evaluating video generation with long temporal dependencies. In this paper, we curate 3 challenging video datasets with long-range dependencies by rendering walks through 3D scenes of procedural mazes, Minecraft worlds, and indoor scans. We perform a comprehensive evaluation of current models and observe their limitations in temporal consistency. Moreover, we introduce the Temporally Consistent Transformer (TECO), a generative model that substantially improves long-term consistency while also reducing sampling time. By compressing its input sequence into fewer embeddings, applying a temporal transformer, and expanding back using a spatial MaskGit, TECO outperforms existing models across many metrics. Videos are available on the website: https://wilson1yan.github.io/teco

arXiv:2210.02303

Imagen Video: High Definition Video Generation with Diffusion Models

We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models. Given a text prompt, Imagen Video generates high definition videos using a base video generation model and a sequence of interleaved spatial and temporal video super-resolution models. We describe how we scale up the system as a high definition text-to-video model including design decisions such as the choice of fully-convolutional temporal and spatial super-resolution models at certain resolutions, and the choice of the v-parameterization of diffusion models. In addition, we confirm and transfer findings from previous work on diffusion-based image generation to the video generation setting. Finally, we apply progressive distillation to our video models with classifier-free guidance for fast, high quality sampling. We find Imagen Video not only capable of generating videos of high fidelity, but also having a high degree of controllability and world knowledge, including the ability to generate diverse videos and text animations in various artistic styles and with 3D object understanding. See https://imagen.research.google/video/ for samples.

arXiv:2209.14792

Make-A-Video: Text-to-Video Generation without Text-Video Data

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in aesthetic, fantastical depictions, etc.) of today's image generation models. We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. First, we decompose the full temporal U-Net and attention tensors and approximate them in space and time. Second, we design a spatial temporal pipeline to generate high resolution and frame rate videos with a video decoder, interpolation model and two super resolution models that can enable various applications besides T2V. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.

arXiv:2209.08289

Continuously Controllable Facial Expression Editing in Talking Face Videos

Recently audio-driven talking face video generation has attracted considerable attention. However, very few researches address the issue of emotional editing of these talking face videos with continuously controllable expressions, which is a strong demand in the industry. The challenge is that speech-related expressions and emotion-related expressions are often highly coupled. Meanwhile, traditional image-to-image translation methods cannot work well in our application due to the coupling of expressions with other attributes such as poses, i.e., translating the expression of the character in each frame may simultaneously change the head pose due to the bias of the training data distribution. In this paper, we propose a high-quality facial expression editing method for talking face videos, allowing the user to control the target emotion in the edited video continuously. We present a new perspective for this task as a special case of motion information editing, where we use a 3DMM to capture major facial movements and an associated texture map modeled by a StyleGAN to capture appearance details. Both representations (3DMM and texture map) contain emotional information and can be continuously modified by neural networks and easily smoothed by averaging in coefficient/latent spaces, making our method simple yet effective. We also introduce a mouth shape preservation loss to control the trade-off between lip synchronization and the degree of exaggeration of the edited expression. Extensive experiments and a user study show that our method achieves state-of-the-art performance across various evaluation criteria.

arXiv:2209.08795

AutoLV: Automatic Lecture Video Generator

We propose an end-to-end lecture video generation system that can generate realistic and complete lecture videos directly from annotated slides, instructor's reference voice and instructor's reference portrait video. Our system is primarily composed of a speech synthesis module with few-shot speaker adaptation and an adversarial learning-based talking-head generation module. It is capable of not only reducing instructors' workload but also changing the language and accent which can help the students follow the lecture more easily and enable a wider dissemination of lecture contents. Our experimental results show that the proposed model outperforms other current approaches in terms of authenticity, naturalness and accuracy. Here is a video demonstration of how our system works, and the outcomes of the evaluation and comparison: https://youtu.be/cY6TYkI0cog.

arXiv:2209.00796공식 코드 · Papers with Code

Diffusion Models: A Comprehensive Survey of Methods and Applications

Diffusion models have emerged as a powerful new family of deep generative models with record-breaking performance in many applications, including image synthesis, video generation, and molecule design. In this survey, we provide an overview of the rapidly expanding body of work on diffusion models, categorizing the research into three key areas: efficient sampling, improved likelihood estimation, and handling data with special structures. We also discuss the potential for combining diffusion models with other generative models for enhanced results. We further review the wide-ranging applications of diffusion models in fields spanning from computer vision, natural language processing, temporal data modeling, to interdisciplinary applications in other scientific disciplines. This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration. Github: https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy.

arXiv:2208.13717

StableFace: Analyzing and Improving Motion Stability for Talking Face Generation

While previous speech-driven talking face generation methods have made significant progress in improving the visual quality and lip-sync quality of the synthesized videos, they pay less attention to lip motion jitters which greatly undermine the realness of talking face videos. What causes motion jitters, and how to mitigate the problem? In this paper, we conduct systematic analyses on the motion jittering problem based on a state-of-the-art pipeline that uses 3D face representations to bridge the input audio and output video, and improve the motion stability with a series of effective designs. We find that several issues can lead to jitters in synthesized talking face video: 1) jitters from the input 3D face representations; 2) training-inference mismatch; 3) lack of dependency modeling among video frames. Accordingly, we propose three effective solutions to address this issue: 1) we propose a gaussian-based adaptive smoothing module to smooth the 3D face representations to eliminate jitters in the input; 2) we add augmented erosions on the input data of the neural renderer in training to simulate the distortion in inference to reduce mismatch; 3) we develop an audio-fused transformer generator to model dependency among video frames. Besides, considering there is no off-the-shelf metric for measuring motion jitters in talking face video, we devise an objective metric (Motion Stability Index, MSI), to quantitatively measure the motion jitters by calculating the reciprocal of variance acceleration. Extensive experimental results show the superiority of our method on motion-stable face video generation, with better quality than previous systems.

arXiv:2208.10922

StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation

We propose StyleTalker, a novel audio-driven talking head generation model that can synthesize a video of a talking person from a single reference image with accurately audio-synced lip shapes, realistic head poses, and eye blinks. Specifically, by leveraging a pretrained image generator and an image encoder, we estimate the latent codes of the talking head video that faithfully reflects the given audio. This is made possible with several newly devised components: 1) A contrastive lip-sync discriminator for accurate lip synchronization, 2) A conditional sequential variational autoencoder that learns the latent motion space disentangled from the lip movements, such that we can independently manipulate the motions and lip movements while preserving the identity. 3) An auto-regressive prior augmented with normalizing flow to learn a complex audio-to-motion multi-modal latent space. Equipped with these components, StyleTalker can generate talking head videos not only in a motion-controllable way when another motion source video is given but also in a completely audio-driven manner by inferring realistic motions from the input audio. Through extensive experiments and user studies, we show that our model is able to synthesize talking head videos with impressive perceptual quality which are accurately lip-synced with the input audios, largely outperforming state-of-the-art baselines.

arXiv:2208.07862공식 코드 · Papers with Code

StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3

Realistic generative face video synthesis has long been a pursuit in both computer vision and graphics community. However, existing face video generation methods tend to produce low-quality frames with drifted facial identities and unnatural movements. To tackle these challenges, we propose a principled framework named StyleFaceV, which produces high-fidelity identity-preserving face videos with vivid movements. Our core insight is to decompose appearance and pose information and recompose them in the latent space of StyleGAN3 to produce stable and dynamic results. Specifically, StyleGAN3 provides strong priors for high-fidelity facial image generation, but the latent space is intrinsically entangled. By carefully examining its latent properties, we propose our decomposition and recomposition designs which allow for the disentangled combination of facial appearance and movements. Moreover, a temporal-dependent model is built upon the decomposed latent features, and samples reasonable sequences of motions that are capable of generating realistic and temporally coherent face videos. Particularly, our pipeline is trained with a joint training strategy on both static images and high-quality video data, which is of higher data efficiency. Extensive experiments demonstrate that our framework achieves state-of-the-art face video generation results both qualitatively and quantitatively. Notably, StyleFaceV is capable of generating realistic $1024\times1024$ face videos even without high-resolution training videos.