Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components. Most of the previous work utilizing motion is deterministic but there are stochastic methods that can model the inherent uncertainty of the future. Existing stochastic models either do not reason about motion explicitly or make limiting assumptions about the static part. In this paper, we reason about appearance and motion in the video stochastically by predicting the future based on the motion history. Explicit reasoning about motion without history already reaches the performance of current stochastic models. The motion history further improves the results by allowing to predict consistent dynamics several frames into the future. Our model performs comparably to the state-of-the-art models on the generic video prediction datasets, however, significantly outperforms them on two challenging real-world autonomous driving datasets with complex motion and dynamic background.
Due to the remarkable progress of deep generative models, animating images has become increasingly efficient, whereas associated results have become increasingly realistic. Current animation-approaches commonly exploit structure representation extracted from driving videos. Such structure representation is instrumental in transferring motion from driving videos to still images. However, such approaches fail in case the source image and driving video encompass large appearance variation. Moreover, the extraction of structure information requires additional modules that endow the animation-model…
Conditional image generation is effective for diverse tasks including training data synthesis for learning-based computer vision. However, despite the recent advances in generative adversarial networks (GANs), it is still a challenging task to generate images with detailed conditioning on object shapes. Existing methods for conditional image generation use category labels and/or keypoints and are only give limited control over object categories. In this work, we present SCGAN, an architecture to generate images with a desired shape specified by an input normal map. The shape-conditioned image …
Given the three dimensional complexity of a video signal, training a robust and diverse GAN based video generative model is onerous due to large stochasticity involved in data space. Learning disentangled representations of the data help to improve robustness and provide control in the sampling process. For video generation, there is a recent progress in this area by considering motion and appearance as orthogonal information and designing architectures that efficiently disentangle them. These approaches rely on handcrafting architectures that impose structural priors on the generator to decom…
Autonomous driving requires efficient reasoning about the location and appearance of the different agents in the scene, which aids in downstream tasks such as object detection, object tracking, and path planning. The past few years have witnessed a surge in approaches that combine the different taskbased modules of the classic self-driving stack into an End-toEnd(E2E) trainable learning system. These approaches replace perception, prediction, and sensor fusion modules with a single contiguous module with shared latent space embedding, from which one extracts a human-interpretable representatio…
Heidelberg Collaboratory for Image Processing（海德堡图像处理合作实验室）；Heidelberg University（海德堡大学）
Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent latent characteristics of an object, especially its appearance and pose. We present a novel approach that learns disentangled representations of these characteristics and explains them individually. Training requires only pairs of images depicting the same object appearance, but no pose annotations. We propose an additional classifier that estimates the minimal a…
In contemporary society, surveillance anomaly detection, i.e., spotting anomalous events such as crimes or accidents in surveillance videos, is a critical task. As anomalies occur rarely, most training data consists of unlabeled videos without anomalous events, which makes the task challenging. Most existing methods use an autoencoder (AE) to learn to reconstruct normal videos; they then detect anomalies based on their failure to reconstruct the appearance of abnormal scenes. However, because anomalies are distinguished by appearance as well as motion, many previous approaches have explicitly …
Recently, a surge of advanced facial editing techniques have been proposed that leverage the generative power of a pre-trained StyleGAN. To successfully edit an image this way, one must first project (or invert) the image into the pre-trained generator's domain. As it turns out, however, StyleGAN's latent space induces an inherent tradeoff between distortion and editability, i.e. between maintaining the original appearance and convincingly altering some of its attributes. Practically, this means it is still challenging to apply ID-preserving facial latent-space editing to faces which are out o…
Appearance-based generic object recognition is a challenging problem because all possible appearances of objects cannot be registered, especially as new objects are produced every day. Function of objects, however, has a comparatively small number of prototypes. Therefore, function-based classification of new objects could be a valuable tool for generic object recognition. Object functions are closely related to hand-object interactions during handling of a functional object; i.e., how the hand approaches the object, which parts of the object and contact the hand, and the shape of the hand dur…
GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；Fudan University（复旦大学）；Zhejiang University（浙江大学）
We present LARNet, a novel end-to-end approach for generating human action videos. A joint generative modeling of appearance and dynamics to synthesize a video is very challenging and therefore recent works in video synthesis have proposed to decompose these two factors. However, these methods require a driving video to model the video dynamics. In this work, we propose a generative approach instead, which explicitly learns action dynamics in latent space avoiding the need of a driving video during inference. The generated action dynamics is integrated with the appearance using a recurrent hie…
Clarkson University（克拉克森大学）；University of Ljubljana（卢布尔雅那大学）
We present GlassesGAN, a novel image editing framework for custom design of glasses, that sets a new standard in terms of image quality, edit realism, and continuous multi-style edit capability. To facilitate the editing process with GlassesGAN, we propose a Targeted Subspace Modelling (TSM) procedure that, based on a novel mechanism for (synthetic) appearance discovery in the latent space of a pre-trained GAN generator, constructs an eyeglasses-specific (latent) subspace that the editing framework can utilize. Additionally, we also introduce an appearance-constrained subspace initialization (…
Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（机器智能与先进计算教育部重点实验室）；Pazhou Lab (HuangPu)（琶洲实验室（黄埔））
Inria（法国国家信息与自动化研究所）；Université Côte d’Azur（蔚蓝海岸大学）；University of Warsaw（华沙大学）
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion. To tackle this challenge, we introduce G$^{3}$AN, a novel spatio-temporal generative model, which seeks to capture the distribution of high dimensional video data and to model appearance and motion in disentangled manner. The latter is achieved by decomposing appearance and motion in a three-stream Generator, where the main stream aims to model spatio-temporal consistency, whereas the two auxiliary streams augment the main stream with multi-scale appearance and mot…
Xiamen University（厦门大学）；PKU-Wuhan Institute for Artificial Intelligence（北京大学-武汉人工智能研究院）
Frame prediction based on AutoEncoder plays a significant role in unsupervised video anomaly detection. Ideally, the models trained on the normal data could generate larger prediction errors of anomalies. However, the correlation between appearance and motion information is underutilized, which makes the models lack an understanding of normal patterns. Moreover, the models do not work well due to the uncontrollable generalizability of deep AutoEncoder. To tackle these problems, we propose a multi-level memory-augmented appearance-motion correspondence framework. The latent correspondence betwe…
S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations
Mercedes-Benz AG（梅赛德斯-奔驰公司）；University of Tübingen（蒂宾根大学）；Institute for Intelligent Systems, Esslingen University of Applied Sciences（埃斯林根应用科学大学智能系统研究所）
Imperial College London（伦敦帝国理工学院）；Stony Brook University（石溪大学）
Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of these factors emulate the entangled variability, giving rise to the rich structure of visual object appearance. Disentangling such unobserved factors from visual data is a challenging task, especially when the data have been captured in uncontrolled recording conditions (also referred to as "in-the-wild") and label information is not available. In this pape…
University of Oxford（牛津大学）；University of Málaga（马拉加大学）
We present LaLaLoc to localise in environments without the need for prior visitation, and in a manner that is robust to large changes in scene appearance, such as a full rearrangement of furniture. Specifically, LaLaLoc performs localisation through latent representations of room layout. LaLaLoc learns a rich embedding space shared between RGB panoramas and layouts inferred from a known floor plan that encodes the structural similarity between locations. Further, LaLaLoc introduces direct, cross-modal pose optimisation in its latent space. Thus, LaLaLoc enables fine-grained pose estimation in …
Nanyang Technological University（南洋理工大学）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
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 prov…
Once Is Enough: Lightweight DiT-Based Video Virtual Try-On via One-Time Garment Appearance Injection
School of computer science, Shanghai key laboratory of data science, Fudan University, China（计算机学院、数据科学重点实验室、复旦大学）；Tencent Youtu Lab, China（腾讯优图实验室）；Shanghai Ocean University, China（上海海洋大学）
University of Tsukuba（筑波大学）；Toyohashi University of Technology（丰桥技术科学大学）
Automatic generation of a high-quality video from a single image remains a challenging task despite the recent advances in deep generative models. This paper proposes a method that can create a high-resolution, long-term animation using convolutional neural networks (CNNs) from a single landscape image where we mainly focus on skies and waters. Our key observation is that the motion (e.g., moving clouds) and appearance (e.g., time-varying colors in the sky) in natural scenes have different time scales. We thus learn them separately and predict them with decoupled control while handling future …
Fudan University（复旦大学）；City University of Hong Kong（香港城市大学）
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 …
DreamLCM: Towards High-Quality Text-to-3D Generation via Latent Consistency Model
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Visual Intelligence + X International Joint Laboratory of the Ministry of Education（教育部视觉智能与X国际联合实验室）；College of Electrical Engineering and Automation, Shandong University of Science and Technology（山东科技大学电气与自动化工程学院）；PengCheng Laboratory（鹏城实验室）
University of California, Los Angeles（加州大学洛杉矶分校）；Hikvision Research Institute（海康威视研究院）
Dynamic patterns are characterized by complex spatial and motion patterns. Understanding dynamic patterns requires a disentangled representational model that separates the factorial components. A commonly used model for dynamic patterns is the state space model, where the state evolves over time according to a transition model and the state generates the observed image frames according to an emission model. To model the motions explicitly, it is natural for the model to be based on the motions or the displacement fields of the pixels. Thus in the emission model, we let the hidden state generat…
University of Electronic Science and Technology of China（电子科技大学）；Alibaba Group（阿里巴巴集团）
Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while preserving the appearance from the source image. In this paper, we propose a novel structure-aware motion modeling approach, the deformable anchor model (DAM), which can automatically discover the motion structure of arbitrary objects without leveraging their prior structure information. Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of mo…
Semantic image synthesis is a process for generating photorealistic images from a single semantic mask. To enrich the diversity of multimodal image synthesis, previous methods have controlled the global appearance of an output image by learning a single latent space. However, a single latent code is often insufficient for capturing various object styles because object appearance depends on multiple factors. To handle individual factors that determine object styles, we propose a class- and layer-wise extension to the variational autoencoder (VAE) framework that allows flexible control over each…
The Pennsylvania State University（宾夕法尼亚州立大学）；University of California, San Diego（加州大学圣地亚哥分校）；NEC Laboratories America（NEC美国实验室）
Conditional image-to-video (cI2V) generation aims to synthesize a new plausible video starting from an image (e.g., a person's face) and a condition (e.g., an action class label like smile). The key challenge of the cI2V task lies in the simultaneous generation of realistic spatial appearance and temporal dynamics corresponding to the given image and condition. In this paper, we propose an approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image. Compared to previous direc…
LVMark: Robust Watermark for Latent Video Diffusion Models
Department of Artificial Intelligence, Korea University, Seoul 02841, Republic of Korea（人工智能系，韩国大学，首尔02841，大韩民国）；Google DeepMind, Mountain View, CA 94043, USA（谷歌DeepMind，山景城，加利福尼亚州94043，美国）
