中文
相关论文

相关论文: A Simple but Strong Baseline for Sounding Video Ge…

200 篇论文

We introduce a multi-modal diffusion model tailored for the bi-directional conditional generation of video and audio. We propose a joint contrastive training loss to improve the synchronization between visual and auditory occurrences. We…

机器学习 · 计算机科学 2024-10-10 Ruihan Yang , Hannes Gamper , Sebastian Braun

Multimodal generative models have shown remarkable progress in single-modality video and audio synthesis, yet truly joint audio-video generation remains an open challenge. In this paper, I explore four key contributions to advance this…

声音 · 计算机科学 2026-03-18 Alejandro Paredes La Torre

The dual-stream transformer architecture-based joint audio-video generation method has become the dominant paradigm in current research. By incorporating pre-trained video diffusion models and audio diffusion models, along with a…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Bingqi Ma , Linlong Lang , Ming Zhang , Dailan He , Xingtong Ge , Yi Zhang , Guanglu Song , Yu Liu

Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to…

声音 · 计算机科学 2025-03-12 Manjie Xu , Chenxing Li , Xinyi Tu , Yong Ren , Rilin Chen , Yu Gu , Wei Liang , Dong Yu

We introduce a novel pipeline for joint audio-visual editing that enhances the coherence between edited video and its accompanying audio. Our approach first applies state-of-the-art video editing techniques to produce the target video, then…

多媒体 · 计算机科学 2026-03-18 Masato Ishii , Akio Hayakawa , Takashi Shibuya , Yuki Mitsufuji

Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…

计算机视觉与模式识别 · 计算机科学 2022-06-24 Jonathan Ho , Tim Salimans , Alexey Gritsenko , William Chan , Mohammad Norouzi , David J. Fleet

This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal…

计算机视觉与模式识别 · 计算机科学 2025-02-26 Akio Hayakawa , Masato Ishii , Takashi Shibuya , Yuki Mitsufuji

We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously, towards high-quality realistic videos. To generate joint audio-video pairs, we propose a novel Multi-Modal…

计算机视觉与模式识别 · 计算机科学 2023-03-27 Ludan Ruan , Yiyang Ma , Huan Yang , Huiguo He , Bei Liu , Jianlong Fu , Nicholas Jing Yuan , Qin Jin , Baining Guo

Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation. However, achieving seamless audio-lip synchronization, maintaining long-term identity consistency, and producing…

计算机视觉与模式识别 · 计算机科学 2024-12-06 Longtao Zheng , Yifan Zhang , Hanzhong Guo , Jiachun Pan , Zhenxiong Tan , Jiahao Lu , Chuanxin Tang , Bo An , Shuicheng Yan

How does audio describe the world around us? In this work, we propose a method for generating images of visual scenes from diverse in-the-wild sounds. This cross-modal generation task is challenging due to the significant information gap…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Kim Sung-Bin , Arda Senocak , Hyunwoo Ha , Tae-Hyun Oh

We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from…

计算机视觉与模式识别 · 计算机科学 2025-02-13 Xiaojuan Wang , Boyang Zhou , Brian Curless , Ira Kemelmacher-Shlizerman , Aleksander Holynski , Steven M. Seitz

This work addresses the lack of multimodal generative models capable of producing high-quality videos with spatially aligned audio. While recent advancements in generative models have been successful in video generation, they often overlook…

声音 · 计算机科学 2026-02-05 Kazuki Shimada , Christian Simon , Takashi Shibuya , Shusuke Takahashi , Yuki Mitsufuji

Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this study, we move…

计算机视觉与模式识别 · 计算机科学 2024-06-14 Weixi Feng , Jiachen Li , Michael Saxon , Tsu-jui Fu , Wenhu Chen , William Yang Wang

We demonstrate how conditional generation from diffusion models can be used to tackle a variety of realistic tasks in the production of music in 44.1kHz stereo audio with sampling-time guidance. The scenarios we consider include…

声音 · 计算机科学 2023-12-06 Mark Levy , Bruno Di Giorgi , Floris Weers , Angelos Katharopoulos , Tom Nickson

Video-to-audio (V2A) generation aims to synthesize realistic and semantically aligned audio from silent videos, with potential applications in video editing, Foley sound design, and assistive multimedia. Although the excellent results,…

Visual and audio modalities are two symbiotic modalities underlying videos, which contain both common and complementary information. If they can be mined and fused sufficiently, performances of related video tasks can be significantly…

计算机视觉与模式识别 · 计算机科学 2017-12-12 Wangli Hao , Zhaoxiang Zhang , He Guan

In this paper, we consider a novel and practical case for talking face video generation. Specifically, we focus on the scenarios involving multi-people interactions, where the talking context, such as audience or surroundings, is present.…

计算机视觉与模式识别 · 计算机科学 2024-02-29 Meidai Xuanyuan , Yuwang Wang , Honglei Guo , Qionghai Dai

Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…

计算机视觉与模式识别 · 计算机科学 2025-09-26 Fangqiu Yi , Jingyu Xu , Jiawei Shao , Chi Zhang , Xuelong Li

Since videos record objects moving coherently, adjacent video frames have commonness (similar object appearances) and uniqueness (slightly changed postures). To prevent redundant modeling of common video signals, we propose a novel…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Mingzhen Sun , Weining Wang , Xinxin Zhu , Jing Liu

We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using…

计算机视觉与模式识别 · 计算机科学 2024-05-03 Burak Can Biner , Farrin Marouf Sofian , Umur Berkay Karakaş , Duygu Ceylan , Erkut Erdem , Aykut Erdem
‹ 上一页 1 2 3 10 下一页 ›