中文
相关论文

相关论文: Latent Temporal Discrepancy as Motion Prior: A Los…

200 篇论文

For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…

图像与视频处理 · 电气工程与系统科学 2022-07-14 Jiahao Li , Bin Li , Yan Lu

Image-conditioned Video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term temporal coherence, especially after fine-tuning. We study the…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Xi Ye , Wenjia Yang , Yangyang Xu , Xiaoyang Liu , Duo Su , Mengfei Xia , Jun Zhu

Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual…

计算机视觉与模式识别 · 计算机科学 2018-08-02 Wei-Sheng Lai , Jia-Bin Huang , Oliver Wang , Eli Shechtman , Ersin Yumer , Ming-Hsuan Yang

We propose the first video diffusion framework for reference-based lineart video colorization. Unlike previous works that rely solely on image generative models to colorize lineart frame by frame, our approach leverages a large-scale…

计算机视觉与模式识别 · 计算机科学 2024-09-20 Zhitong Huang , Mohan Zhang , Jing Liao

With the concept of teaching being introduced to the machine learning community, a teacher model start using dynamic loss functions to teach the training of a student model. The dynamic intends to set adaptive loss functions to different…

人工智能 · 计算机科学 2023-10-31 Zhoyang Hai , Liyuan Pan , Xiabi Liu , Zhengzheng Liu , Mirna Yunita

Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework…

计算机视觉与模式识别 · 计算机科学 2026-01-14 Xindi Wu , Despoina Paschalidou , Jun Gao , Antonio Torralba , Laura Leal-Taixé , Olga Russakovsky , Sanja Fidler , Jonathan Lorraine

Video-LLMs often attend to irrelevant frames, which is especially detrimental for sports coaching tasks requiring precise temporal grounding. Yet obtaining frame-level supervision is challenging: expensive to collect from humans and…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Arushi Rai , Adriana Kovashka

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…

机器人学 · 计算机科学 2022-05-27 Stefan Wapnick , Travis Manderson , David Meger , Gregory Dudek

Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artifacts and temporal drift. We hypothesize that the view…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Su Sun , Cheng Zhao , Himangi Mittal , Gaurav Mittal , Rohith Kukkala , Yingjie Victor Chen , Mei Chen

Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied…

机器学习 · 计算机科学 2026-04-08 Masoud S. Sakha , Rushikesh Kamalapurkar , Sean Meyn

The motion transfer task aims to transfer motion from a source video to newly generated videos, requiring the model to decouple motion from appearance. Previous diffusion-based methods primarily rely on separate spatial and temporal…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Qingyu Shi , Jianzong Wu , Jinbin Bai , Jiangning Zhang , Lu Qi , Yunhai Tong , Xiangtai Li

Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion…

计算机视觉与模式识别 · 计算机科学 2021-10-25 Muhammad Kashif Ali , Sangjoon Yu , Tae Hyun Kim

Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Weifeng Chen , Yatai Ji , Jie Wu , Hefeng Wu , Pan Xie , Jiashi Li , Xin Xia , Xuefeng Xiao , Liang Lin

Recent advances in video generation models have achieved impressive results. However, these models heavily rely on the use of high-quality data that combines both high visual quality and high motion quality. In this paper, we identify a key…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Xiangyang Luo , Qingyu Li , Yuming Li , Guanbo Huang , Yongjie Zhu , Wenyu Qin , Meng Wang , Pengfei Wan , Shao-Lun Huang

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion…

机器学习 · 计算机科学 2025-04-02 Bac Nguyen , Chieh-Hsin Lai , Yuhta Takida , Naoki Murata , Toshimitsu Uesaka , Stefano Ermon , Yuki Mitsufuji

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…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Dennis Menn , Chih-Hsien Chou

Significant advancements have been made in video generative models recently. Unlike image generation, video generation presents greater challenges, requiring not only generating high-quality frames but also ensuring temporal consistency…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Jiahe Liu , Youran Qu , Qi Yan , Xiaohui Zeng , Lele Wang , Renjie Liao

Leveraging the generative ability of image diffusion models offers great potential for zero-shot video-to-video translation. The key lies in how to maintain temporal consistency across generated video frames by image diffusion models.…

计算机视觉与模式识别 · 计算机科学 2023-11-02 Yuxiang Bao , Di Qiu , Guoliang Kang , Baochang Zhang , Bo Jin , Kaiye Wang , Pengfei Yan

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for visual recognition problems. Nevertheless, the convolutional filters in these networks are local operations while ignoring the large-range dependency.…

计算机视觉与模式识别 · 计算机科学 2019-06-14 Zhaofan Qiu , Ting Yao , Chong-Wah Ngo , Xinmei Tian , Tao Mei