Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and inpainting, which accumulate errors during inference due to incorrect intermediary outputs, non-differentiable processes, and separate models. To overcome these limitations, we introduce ``geometry-as-context". It iteratively completes the following steps using an autoregressive camera-controlled video generation model: (1) estimates the geometry of the current view necessary for 3D reconstruction, and (2) simulates and restores novel view images rendered by the 3D scene. Under this multi-task framework, we develop the camera gated attention module to enhance the model's capability to effectively leverage camera poses. During the training phase, text contexts are utilized to ascertain whether geometric or RGB images should be generated. To ensure that the model can generate RGB-only outputs during inference, the geometry context is randomly dropped from the interleaved text-image-geometry training sequence. The method has been tested on scene video generation with one-direction and forth-and-back trajectories. The results show its superiority over previous approaches in maintaining scene consistency and camera control.
Leibniz University Hannover（汉诺威莱布尼茨大学）；University of Bonn（波恩大学）；University of Twente（特文特大学）
As a natural extension of the image synthesis task, video synthesis has attracted a lot of interest recently. Many image synthesis works utilize class labels or text as guidance. However, neither labels nor text can provide explicit temporal guidance, such as when an action starts or ends. To overcome this limitation, we introduce semantic video scene graphs as input for video synthesis, as they represent the spatial and temporal relationships between objects in the scene. Since video scene graphs are usually temporally discrete annotations, we propose a video scene graph (VSG) encoder that no…
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）
Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a two-stage MOtion, Scene and Object decomposition framework (MOSO) for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSO-Transformer predicts the object and sce…
CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
The University of Hong Kong（香港大学）；Kling Team, Kuaishou Technology（快手技术 Kling 团队）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；Microsoft Research Project Page（微软研究院项目页面）
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Peng Cheng Laboratory（鹏城实验室）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional architecture that untangles the scene's foreground from the background. Experiments suggest this model can generate tiny videos up to a second at full frame rate better than simple baselines, and we show its utility at predicting plausible futures of static images. Moreover, experiments and visualiz…
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Bonn（波恩大学）
Training GANs in low-data regimes remains a challenge, as overfitting often leads to memorization or training divergence. In this work, we introduce One-Shot GAN that can learn to generate samples from a training set as little as one image or one video. We propose a two-branch discriminator, with content and layout branches designed to judge the internal content separately from the scene layout realism. This allows synthesis of visually plausible, novel compositions of a scene, with varying content and layout, while preserving the context of the original sample. Compared to previous single-ima…
Block Modulating Video Compression: An Ultra Low Complexity Image Compression Encoder for Resource Limited Platforms
Boston University（波士顿大学）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；New Jersey Institute of Technology（新泽西理工学院）；Weill Cornell Medicine（威尔康奈尔医学院）；Beijing University of Posts and Telecommunications（北京邮电大学）；Bell Labs（贝尔实验室）；Westlake University（西湖大学）
Progressive Depth Decoupling and Modulating for Flexible Depth Completion
School of Automation, Hangzhou Dianzi University（杭州电子科技大学自动化学院）；School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Communication Engineering, Hangzhou Dianzi University（杭州电子科技大学通信工程学院）；Lishui Institute of Hangzhou Dianzi University（杭州电子科技大学丽水研究院）
Shanghai University（上海大学）；Shanghai Institute for Advanced Communication and Data Science（上海先进通信与数据科学研究院）
Recently, video scene text detection has received increasing attention due to its comprehensive applications. However, the lack of annotated scene text video datasets has become one of the most important problems, which hinders the development of video scene text detection. The existing scene text video datasets are not large-scale due to the expensive cost caused by manual labeling. In addition, the text instances in these datasets are too clear to be a challenge. To address the above issues, we propose a tracking based semi-automatic labeling strategy for scene text videos in this paper. We …
Video ads segmentation and tagging is a challenging task due to two main reasons: (1) the video scene structure is complex and (2) it includes multiple modalities (e.g., visual, audio, text.). While previous work focuses mostly on activity videos (e.g. "cooking", "sports"), it is not clear how they can be leveraged to tackle the task of video ads content structuring. In this paper, we propose a two-stage method that first provides the boundaries of the scenes, and then combines a confidence score for each segmented scene and the tag classes predicted for that scene. We provide extensive experi…
Washington University（华盛顿大学）；Tsinghua University（清华大学）
This paper proposes an algorithm that turns a regular video capturing urban scenes into a high-quality endless animation, known as a Cinemagraph. The creation of a Cinemagraph usually requires a static camera in a carefully configured scene. The task becomes challenging for a regular video with a moving camera and objects. Our approach first warps an input video into the viewpoint of a reference camera. Based on the warped video, we propose effective temporal analysis algorithms to detect regions with static geometry and dynamic appearance, where geometric modeling is reliable and visually att…
