中文
相关论文

相关论文: Temporal Realism Evaluation of Generated Videos Us…

200 篇论文

Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals. For video representations, however, mapping…

计算机视觉与模式识别 · 计算机科学 2023-08-08 Joo Chan Lee , Daniel Rho , Jong Hwan Ko , Eunbyung Park

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

图像与视频处理 · 电气工程与系统科学 2024-10-28 Ruihan Yang , Yibo Yang , Joseph Marino , Stephan Mandt

Realistic temporal dynamics are crucial for many video generation, processing and modelling applications, e.g. in computational fluid dynamics, weather prediction, or long-term climate simulations. Video diffusion models (VDMs) are the…

Evaluating object removal in images and videos remains challenging because the task is inherently one-to-many, yet existing metrics frequently disagree with human perception. Full-reference metrics reward copy-paste behaviors over genuine…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Fuhao Li , Shaofeng You , Jiagao Hu , Yu Liu , Yuxuan Chen , Zepeng Wang , Fei Wang , Daiguo Zhou , Jian Luan

Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the…

计算机视觉与模式识别 · 计算机科学 2022-04-15 Takashi Isobe , Xu Jia , Xin Tao , Changlin Li , Ruihuang Li , Yongjie Shi , Jing Mu , Huchuan Lu , Yu-Wing Tai

Fr\'echet Video Distance (FVD), a prominent metric for evaluating video generation models, is known to conflict with human perception occasionally. In this paper, we aim to explore the extent of FVD's bias toward per-frame quality over…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Songwei Ge , Aniruddha Mahapatra , Gaurav Parmar , Jun-Yan Zhu , Jia-Bin Huang

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Chenyu Yang , Xuan Dong , Xizhou Zhu , Weijie Su , Jiahao Wang , Hao Tian , Zhe Chen , Wenhai Wang , Lewei Lu , Jifeng Dai

Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames. Yet for human video synthesis, such scheme is less reliable due to the…

计算机视觉与模式识别 · 计算机科学 2020-12-14 Lingbo Yang , Zhanning Gao , Peiran Ren , Siwei Ma , Wen Gao

Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into…

计算机视觉与模式识别 · 计算机科学 2022-02-28 Yifan Liu , Chunhua Shen , Changqian Yu , Jingdong Wang

As super-resolution (SR) techniques introduce unique distortions that fundamentally differ from those caused by traditional degradation processes (e.g., compression), there is an increasing demand for specialized video quality assessment…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Yixiao Li , Xiaoyuan Yang , Weide Liu , Xin Jin , Xu Jia , Yukun Lai , Paul L Rosin , Haotao Liu , Wei Zhou

In this paper, we propose a quality enhancement network of versatile video coding (VVC) compressed videos by jointly exploiting spatial details and temporal structure (SDTS). The proposed network consists of a temporal structure fusion…

计算机视觉与模式识别 · 计算机科学 2019-05-23 Xiandong Meng , Xuan Deng , Shuyuan Zhu , Bing Zeng

Real-world low-resolution (LR) videos have diverse and complex degradations, imposing great challenges on video super-resolution (VSR) algorithms to reproduce their high-resolution (HR) counterparts with high quality. Recently, the…

计算机视觉与模式识别 · 计算机科学 2024-07-15 Xi Yang , Chenhang He , Jianqi Ma , Lei Zhang

Virtual viewpoints synthesis is an essential process for many immersive applications including Free-viewpoint TV (FTV). A widely used technique for viewpoints synthesis is Depth-Image-Based-Rendering (DIBR) technique. However, such…

多媒体 · 计算机科学 2019-03-29 Suiyi Ling , Jing Li , Zhaohui Che , Xiongkuo Min , Guangtao Zhai , Patrick Le Callet

The pursuit of higher compression efficiency continuously drives the advances of video coding technologies. Fundamentally, we wish to find better "predictions" or "priors" that are reconstructed previously to remove the signal dependency…

图像与视频处理 · 电气工程与系统科学 2019-02-22 Haojie Liu , Tong Chen , Ming Lu , Qiu Shen , Zhan Ma

Evaluating the robustness of Video classification models is very challenging, specifically when compared to image-based models. With their increased temporal dimension, there is a significant increase in complexity and computational cost.…

Video restoration (VR) aims to recover high-quality videos from degraded ones. Although recent zero-shot VR methods using pre-trained diffusion models (DMs) show good promise, they suffer from approximation errors during reverse diffusion…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Hengkang Wang , Yang Liu , Huidong Liu , Chien-Chih Wang , Yanhui Guo , Hongdong Li , Bryan Wang , Ju Sun

We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal…

计算机视觉与模式识别 · 计算机科学 2021-06-04 Xun Yang , Fuli Feng , Wei Ji , Meng Wang , Tat-Seng Chua

Neural Representations for Videos (NeRV) has emerged as a promising implicit neural representation (INR) approach for video analysis, which represents videos as neural networks with frame indexes as inputs. However, NeRV-based methods are…

计算机视觉与模式识别 · 计算机科学 2025-01-20 Jialong Guo , Ke liu , Jiangchao Yao , Zhihua Wang , Jiajun Bu , Haishuai Wang

Text-to-video diffusion models have advanced video generation significantly. However, customizing these models to generate videos with tailored motions presents a substantial challenge. In specific, they encounter hurdles in (a) accurately…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Hyeonho Jeong , Geon Yeong Park , Jong Chul Ye

Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Daowen Li , Ruixiao Dong , Ying Chen , Kai Li , Ding Ding , Li Li