We introduce Gen4P, a unified framework for recovering 4D geometry and motion from monocular video. We show that a pretrained video generator can be repurposed into a feed-forward 4D perceiver without iterative denoising. Building on on-demand querying, Gen4P processes clean video latents in a single encoder pass and predicts the requested 4D attributes through a lightweight cross-attention decoder. The on-demand query formulation enables flexible spatial sampling, and our proposed continuous-time queries further provide temporal flexibility. To strengthen geometric knowledge, we propose a straightforward plug-in solution by incorporating a pretrained video-depth LoRA as a frozen geometry prior, improving overall performance without adding extra trainable parameters. Gen4P achieves state-of-the-art or competitive performance on tasks of 3D point tracking, video depth and camera pose estimation. Qualitative results on in-the-wild videos illustrate its capability of tracking complex motion while maintaining the delicate structure. Together, these results demonstrate the potential of video generative pretraining for unified 4D perception. See this https URL for more visual results.
Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver - a model that builds upon Transformers and hence makes few arch…
Generic Boundary Detection (GBD) aims at locating the general boundaries that divide videos into semantically coherent and taxonomy-free units, and could serve as an important pre-processing step for long-form video understanding. Previous works often separately handle these different types of generic boundaries with specific designs of deep networks from simple CNN to LSTM. Instead, in this paper, we present Temporal Perceiver, a general architecture with Transformer, offering a unified solution to the detection of arbitrary generic boundaries, ranging from shot-level, event-level, to scene-l…
We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with linear complexity, in contrast to the quadratic complexity of self-attention used in many state-of-the-art transformer-based models. To further improve the efficiency of our framework, we also study applying LayerDrop on cross-attention layers and introduce a mixed-stream architecture for cross-modal retrieval. We evaluate Perceiver-VL on diverse video-text and i…
SVFAP: Self-supervised Video Facial Affect Perceiver
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Tsinghua University（清华大学）
Tsinghua University（清华大学）；University of Science and Technology Beijing（北京科技大学）
Video generation has achieved rapid progress benefiting from high-quality renderings provided by powerful image generators. We regard the video synthesis task as generating a sequence of images sharing the same contents but varying in motions. However, most previous video synthesis frameworks based on pre-trained image generators treat content and motion generation separately, leading to unrealistic generated videos. Therefore, we design a novel framework to build the motion space, aiming to achieve content consistency and fast convergence for video generation. We present MotionVideoGAN, a nov…
Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics. Recently, autoregressive latent video models have proved to be a powerful video prediction tool, by separating the video prediction into two sub-problems: pre-training an image generator model, followed by learning an autoregressive prediction model in the latent space of the image generator. However, successfully generating high-fidelity and high-resolution videos has yet to be seen. In this work, we investigate how to train an autoregressive latent …
Rutgers University（罗格斯大学）；Snap Inc.（Snap公司）；University of Delaware（特拉华大学）
Image and video synthesis are closely related areas aiming at generating content from noise. While rapid progress has been demonstrated in improving image-based models to handle large resolutions, high-quality renderings, and wide variations in image content, achieving comparable video generation results remains problematic. We present a framework that leverages contemporary image generators to render high-resolution videos. We frame the video synthesis problem as discovering a trajectory in the latent space of a pre-trained and fixed image generator. Not only does such a framework render high…
Purdue University（普渡大学）；Baidu Research - Institute of Deep Learning（百度研究院深度学习研究所）；Facebook（脸书）
We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video. Our hierarchical framework contains a sentence generator and a paragraph generator. The sentence generator produces one simple short sentence that describes a specific short video interval. It exploits both temporal- and spatial-attention mechanisms to selectively focus on visual elements during generation. The paragraph generator captures the inter-sentence dependency by taking as input the sententi…
When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators
Zhejiang University of Technology（浙江工业大学）；University of New South Wales (UNSW Sydney)（新南威尔士大学（悉尼））；University of Auckland（奥克兰大学）；Zhejiang University（浙江大学）
Korea Advanced Institute of Science and Technology（韩国科学技术院）
Advances in technology have led to the development of methods that can create desired visual multimedia. In particular, image generation using deep learning has been extensively studied across diverse fields. In comparison, video generation, especially on conditional inputs, remains a challenging and less explored area. To narrow this gap, we aim to train our model to produce a video corresponding to a given text description. We propose a novel training framework, Text-to-Image-to-Video Generative Adversarial Network (TiVGAN), which evolves frame-by-frame and finally produces a full-length vid…
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
Tsinghua University（清华大学）；Nanyang Technological University（南洋理工大学）；University of Waterloo（滑铁卢大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））
We present an efficient framework that can generate a coherent paragraph to describe a given video. Previous works on video captioning usually focus on video clips. They typically treat an entire video as a whole and generate the caption conditioned on a single embedding. On the contrary, we consider videos with rich temporal structures and aim to generate paragraph descriptions that can preserve the story flow while being coherent and concise. Towards this goal, we propose a new approach, which produces a descriptive paragraph by assembling temporally localized descriptions. Given a video, it…
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局信息通信研究院）
UT Austin（德克萨斯大学奥斯汀分校）；U of Oregon（俄勒冈大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）
Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without any training or optimization) by leveraging the power of existing text-to-image synthesis methods (e.g., Stable Diffusion), making them suitable for the video domain. Our key modifications include (i) enriching the latent codes of the generated frames with motion dynamics to keep the global scene and the background time consistent; and (ii) reprogramming fra…
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…
The Macau University of Science and Technology（澳门科技大学）
While deep learning (DL)-based video deraining methods have achieved significant success recently, they still exist two major drawbacks. Firstly, most of them do not sufficiently model the characteristics of rain layers of rainy videos. In fact, the rain layers exhibit strong physical properties (e.g., direction, scale and thickness) in spatial dimension and natural continuities in temporal dimension, and thus can be generally modelled by the spatial-temporal process in statistics. Secondly, current DL-based methods seriously depend on the labeled synthetic training data, whose rain types are …
Tencent AI Lab（腾讯人工智能实验室）；Southeast University（东南大学）；Columbia University（哥伦比亚大学）
Temporal action proposal generation is an important task, aiming to localize the video segments containing human actions in an untrimmed video. In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information. First, we propose to use a bilinear matching model to exploit the rich local information within the video sequence. Afterwards, two components, namely segment proposal producer (SPP) and frame actionness producer (FAP), are co…
We propose a novel method for generating high-resolution videos of talking-heads from speech audio and a single 'identity' image. Our method is based on a convolutional neural network model that incorporates a pre-trained StyleGAN generator. We model each frame as a point in the latent space of StyleGAN so that a video corresponds to a trajectory through the latent space. Training the network is in two stages. The first stage is to model trajectories in the latent space conditioned on speech utterances. To do this, we use an existing encoder to invert the generator, mapping from each video fra…
UiT The Arctic University of Norway（挪威特罗姆瑟大学（北极大学））；Carnegie Mellon University（卡内基梅隆大学）
Video summarization plays an important role in video understanding by selecting key frames/shots. Traditionally, it aims to find the most representative and diverse contents in a video as short summaries. Recently, a more generalized task, query-conditioned video summarization, has been introduced, which takes user queries into consideration to learn more user-oriented summaries. In this paper, we propose a query-conditioned three-player generative adversarial network to tackle this challenge. The generator learns the joint representation of the user query and the video content, and the discri…
FlowCred: Hierarchical Credit Assignment and Functional Coordination for Joint Text-to-Video Post-Training
Shanghai Jiao Tong University（上海交通大学）；KlingAI；The Hong Kong University of Science and Technology（香港科技大学）；South China University of Technology（华南理工大学）；The University of Hong Kong（香港大学）
EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection
N2TP Technology Solution JSC（N2TP技术解决方案有限公司）；College of Technology, National Economics University（国家经济大学技术学院）；University of Science, Vietnam National University（越南国家大学科学大学）；Faculty of AI and Data Science, Phenikaa University（Phenikaa大学人工智能与数据科学学院）；The Saigon International University（西贡国际大学）；College of Informatics, Yuan Ze University（元智大学资讯学院）
Learning Human Skill Generators at Key-Step Levels
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；Shanghai AI Lab（上海人工智能实验室）
Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；Show Lab, National University of Singapore（新加坡国立大学Show实验室）
Training of Generative Adversarial Network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation. In general, the computational cost of training GAN scales exponentially with the resolution. In this study, we present a novel memory efficient method of unsupervised learning of high-resolution video dataset whose computational cost scales only linearly with the resolution. We achieve this by designing the generator model as a stack of small sub-generators and training the model in a specific way. We train each sub-generator with i…
Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning
School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China（中国教育部可持续城市智能交通工程研究中心）
TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection
Zhejiang University（浙江大学）；University of the Chinese Academy of Sciences（中国科学院大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；Zhejiang Gongshang University（浙江工商大学）
Facebook AI（Facebook人工智能）；Columbia University（哥伦比亚大学）；Univesity of Edinburgh（爱丁堡大学）
Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost. While this avoids flow computation, it also hurts accuracy since the motion vector is noisy and has substantially reduced resolution, which makes it a less discriminative motion representation. To remedy these issues, we propose a lightweight generator network, which reduces noises in …
This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2020 Task 1 (\textbf{temporal action localization/detection}). Temporal action localization requires to not only precisely locate the temporal boundaries of action instances, but also accurately classify the untrimmed videos into specific categories. In this paper, we decouple the temporal action localization task into two stages (i.e. proposal generation and classification) and enrich the proposal diversity through exhaustively exploring the influences of multiple components from differe…
