English
Related papers

Related papers: FLAVR: Flow-Agnostic Video Representations for Fas…

200 papers

Video frame interpolation (VFI) works generally predict intermediate frame(s) by first estimating the motion between inputs and then warping the inputs to the target time with the estimated motion. This approach, however, is not optimal…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Dawit Mureja Argaw , In So Kweon

Estimating per-pixel motion between video frames, known as optical flow, is a long-standing problem in video understanding and analysis. Most contemporary optical flow techniques largely focus on addressing the cross-image matching with…

Computer Vision and Pattern Recognition · Computer Science 2022-02-09 Ao Luo , Fan Yang , Kunming Luo , Xin Li , Haoqiang Fan , Shuaicheng Liu

With the prosper of video diffusion models, down-stream applications like video editing have been significantly promoted without consuming much computational cost. One particular challenge in this task lies at the motion transfer process…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Ge Wang , Songlin Fan , Hangxu Liu , Quanjian Song , Hewei Wang , Jinfeng Xu

Face video restoration (FVR) is a challenging but important problem where one seeks to recover a perceptually realistic face videos from a low-quality input. While diffusion probabilistic models (DPMs) have been shown to achieve remarkable…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Zihao Zou , Jiaming Liu , Shirin Shoushtari , Yubo Wang , Weijie Gan , Ulugbek S. Kamilov

Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Wonyong Seo , Jihyong Oh , Munchurl Kim

For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation between video frames to aggregate information from multiple frames…

Computer Vision and Pattern Recognition · Computer Science 2021-08-27 Hyeongseok Son , Junyong Lee , Jonghyeop Lee , Sunghyun Cho , Seungyong Lee

A common strategy to video understanding is to incorporate spatial and motion information by fusing features derived from RGB frames and optical flow. In this work, we introduce a new way to leverage semantic segmentation as an intermediate…

Computer Vision and Pattern Recognition · Computer Science 2021-04-16 Juhana Kangaspunta , AJ Piergiovanni , Rico Jonschkowski , Michael Ryoo , Anelia Angelova

We propose a visual SLAM method by predicting and updating line flows that represent sequential 2D projections of 3D line segments. While feature-based SLAM methods have achieved excellent results, they still face problems in challenging…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Qiuyuan Wang , Zike Yan , Junqiu Wang , Fei Xue , Wei Ma , Hongbin Zha

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Ruyi Xu , Guangxuan Xiao , Yukang Chen , Liuning He , Kelly Peng , Yao Lu , Song Han

Learning latent actions from large-scale videos is crucial for the pre-training of scalable embodied foundation models, yet existing methods often struggle with action-irrelevant distractors. Although incorporating action supervision can…

Robotics · Computer Science 2026-03-24 Xizhou Bu , Jiexi Lyu , Fulei Sun , Ruichen Yang , Zhiqiang Ma , Wei Li

In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Shuangrui Ding , Weidi Xie , Yabo Chen , Rui Qian , Xiaopeng Zhang , Hongkai Xiong , Qi Tian

Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories. However, the hand-crafted flow-based processes in these methods are applied…

Image and Video Processing · Electrical Eng. & Systems 2022-04-08 Zhen Li , Cheng-Ze Lu , Jianhua Qin , Chun-Le Guo , Ming-Ming Cheng

In many real-world scenarios, recorded videos suffer from accidental focus blur, and while video deblurring methods exist, most specifically target motion blur or spatial-invariant blur. This paper introduces a framework optimized for the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Crispian Morris , Nantheera Anantrasirichai , Fan Zhang , David Bull

Video generation, while capable of generating realistic videos, is computationally expensive and slow, prohibiting real-time applications. In this paper, we observe that video latents encoded via an autoencoder under the Latent Diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Dennis Menn , Chih-Hsien Chou

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Linchao Zhu , Laura Sevilla-Lara , Du Tran , Matt Feiszli , Yi Yang , Heng Wang

Video frame interpolation and prediction aim to synthesize frames in-between and subsequent to existing frames, respectively. Despite being closely-related, these two tasks are traditionally studied with different model architectures, or…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Xin Jin , Longhai Wu , Jie Chen , Ilhyun Cho , Cheul-Hee Hahm

Differentiable image sampling in the form of backward warping has seen broad adoption in tasks like depth estimation and optical flow prediction. In contrast, how to perform forward warping has seen less attention, partly due to additional…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Simon Niklaus , Feng Liu

With the advance in user-friendly and powerful video editing tools, anyone can easily manipulate videos without leaving prominent visual traces. Frame-rate up-conversion (FRUC), a representative temporal-domain operation, increases the…

Multimedia · Computer Science 2021-03-26 Minseok Yoon , Seung-Hun Nam , In-Jae Yu , Wonhyuk Ahn , Myung-Joon Kwon , Heung-Kyu Lee

We propose a novel video frame interpolation algorithm based on asymmetric bilateral motion estimation (ABME), which synthesizes an intermediate frame between two input frames. First, we predict symmetric bilateral motion fields to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Junheum Park , Chul Lee , Chang-Su Kim

We predict future video frames from complex dynamic scenes, using an invertible neural network as the encoder of a nonlinear dynamic system with latent linear state evolution. Our invertible linear embedding (ILE) demonstrates successful…

Computer Vision and Pattern Recognition · Computer Science 2019-03-04 Robert Pottorff , Jared Nielsen , David Wingate