English
Related papers

Related papers: FastInit: Fast Noise Initialization for Temporally…

200 papers

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Deng Huang , Wenhao Wu , Weiwen Hu , Xu Liu , Dongliang He , Zhihua Wu , Xiangmiao Wu , Mingkui Tan , Errui Ding

Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computational and data resources, posing a challenge to developing…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Yu Lu , Yuanzhi Liang , Linchao Zhu , Yi Yang

In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation streams. Existing approaches typically utilize external…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Hao Wu , Fan Xu , Chong Chen , Xian-Sheng Hua , Xiao Luo , Haixin Wang

Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remark- able capabilities. However, their practical deployment is of- ten hindered by slow inference speeds and high memory con-…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Sijie Wang , Qiang Wang , Shaohuai Shi

This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-14 Chaeyoung Jung , Suyeon Lee , Ji-Hoon Kim , Joon Son Chung

Diffusion-based video generation has achieved significant progress, yet generating multiple actions that occur sequentially remains a formidable task. Directly generating a video with sequential actions can be extremely challenging due to…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Bowen Zhang , Xiaofei Xie , Haotian Lu , Na Ma , Tianlin Li , Qing Guo

The Reflow operation aims to straighten the inference trajectories of the rectified flow during training by constructing deterministic couplings between noises and images, thereby improving the quality of generated images in single-step or…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Jimin Dai , Jiexi Yan , Jian Yang , Lei Luo

While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Yijing Tu , Shaojin Wu , Mengqi Huang , Wenchuan Wang , Yuxin Wang , Chunxiao Liu , Zhendong Mao

Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Jigang Duan , Genwei Ma , Xu Jiang , Wenfeng Xu , Ping Yang , Xing Zhao

Recent research demonstrate that prediction of time series by recurrent neural networks (RNNs) based on the noisy input generates a smooth anticipated trajectory. We examine the internal dynamics of RNNs and establish a set of conditions…

Machine Learning · Computer Science 2020-10-07 Boris Rubinstein

Fine-tuning Stable Diffusion enables subject-driven image synthesis by adapting the model to generate images containing specific subjects. However, existing fine-tuning methods suffer from two key issues: underfitting, where the model fails…

Graphics · Computer Science 2025-06-10 Yao Ni , Song Wen , Piotr Koniusz , Anoop Cherian

Image style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos. Some video style transfer models have been proposed to improve temporal consistency, yet they fail to…

Computer Vision and Pattern Recognition · Computer Science 2018-11-02 Chang Gao , Derun Gu , Fangjun Zhang , Yizhou Yu

In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. We leverage an…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Xin Li , Wenqing Chu , Ye Wu , Weihang Yuan , Fanglong Liu , Qi Zhang , Fu Li , Haocheng Feng , Errui Ding , Jingdong Wang

Contemporary text-to-image models exhibit a surprising degree of mode collapse, as can be seen when sampling several images given the same text prompt. Previous work has attempted to address this issue by steering the model using guidance…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Anne Harrington , A. Sophia Koepke , Shyamgopal Karthik , Trevor Darrell , Alexei A. Efros

Text-to-image diffusion models, such as Stable Diffusion, can produce high-quality and diverse images but often fail to achieve compositional alignment, particularly when prompts describe complex object relationships, attributes, or spatial…

Recent text-to-video (T2V) diffusion models have made remarkable progress in generating high-quality videos. However, they often struggle to align with complex text prompts, particularly when multiple objects, attributes, or spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Daeun Lee , Jaehong Yoon , Jaemin Cho , Mohit Bansal

Denoising is a crucial step in many video processing pipelines such as in interactive editing, where high quality, speed, and user control are essential. While recent approaches achieve significant improvements in denoising quality by…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Xin Jin , Simon Niklaus , Zhoutong Zhang , Zhihao Xia , Chunle Guo , Yuting Yang , Jiawen Chen , Chongyi Li

Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and the limited availability of video-text datasets. Recent…

Computer Vision and Pattern Recognition · Computer Science 2024-10-04 Xiefan Guo , Jinlin Liu , Miaomiao Cui , Liefeng Bo , Di Huang

We explore inference-time scaling in text-guided 3D diffusion models to enhance generative quality without additional training. To this end, we introduce ITS3D, a framework that formulates the task as an optimization problem to identify the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Zhenglin Zhou , Fan Ma , Xiaobo Xia , Hehe Fan , Yi Yang , Tat-Seng Chua

High-resolution (HR) videos play a crucial role in many computer vision applications. Although existing video restoration (VR) methods can significantly enhance video quality by exploiting temporal information across video frames, they are…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Mary Aiyetigbo , Wanqi Yuan , Feng Luo , Nianyi Li