中文
相关论文

相关论文: MEGADance: Mixture-of-Experts Architecture for Gen…

200 篇论文

Music mixing involves combining individual tracks into a cohesive mixture, a task characterized by subjectivity where multiple valid solutions exist for the same input. Existing automatic mixing systems treat this task as a deterministic…

音频与语音处理 · 电气工程与系统科学 2025-11-12 Eloi Moliner , Marco A. Martínez-Ramírez , Junghyun Koo , Wei-Hsiang Liao , Kin Wai Cheuk , Joan Serrà , Vesa Välimäki , Yuki Mitsufuji

Dancing to music is one of human's innate abilities since ancient times. In machine learning research, however, synthesizing dance movements from music is a challenging problem. Recently, researchers synthesize human motion sequences…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Ruozi Huang , Huang Hu , Wei Wu , Kei Sawada , Mi Zhang , Daxin Jiang

While generative artificial intelligence has advanced significantly across text, image, audio, and video domains, 3D generation remains comparatively underdeveloped due to fundamental challenges such as data scarcity, algorithmic…

Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of domains and private data. Recent image transfer works show the…

计算机视觉与模式识别 · 计算机科学 2023-12-13 Wenjie Yin , Yi Yu , Hang Yin , Danica Kragic , Mårten Björkman

Human motion synthesis conditioned on textual input has gained significant attention in recent years due to its potential applications in various domains such as gaming, film production, and virtual reality. Conditioned Motion synthesis…

计算机视觉与模式识别 · 计算机科学 2025-01-06 Avinash Amballa , Gayathri Akkinapalli , Vinitra Muralikrishnan

The burgeoning growth of video-to-music generation can be attributed to the ascendancy of multimodal generative models. However, there is a lack of literature that comprehensively combs through the work in this field. To fill this gap, this…

音频与语音处理 · 电气工程与系统科学 2025-12-23 Shulei Ji , Songruoyao Wu , Zihao Wang , Shuyu Li , Kejun Zhang

Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the…

The recent success in StyleGAN demonstrates that pre-trained StyleGAN latent space is useful for realistic video generation. However, the generated motion in the video is usually not semantically meaningful due to the difficulty of…

计算机视觉与模式识别 · 计算机科学 2022-10-24 Seung Hyun Lee , Gyeongrok Oh , Wonmin Byeon , Chanyoung Kim , Won Jeong Ryoo , Sang Ho Yoon , Hyunjun Cho , Jihyun Bae , Jinkyu Kim , Sangpil Kim

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

Generating 3D human motions from text is a challenging yet valuable task. The key aspects of this task are ensuring text-motion consistency and achieving generation diversity. Although recent advancements have enabled the generation of…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Zheng Qin , Yabing Wang , Minghui Yang , Sanping Zhou , Ming Yang , Le Wang

We propose Lodge++, a choreography framework to generate high-quality, ultra-long, and vivid dances given the music and desired genre. To handle the challenges in computational efficiency, the learning of complex and vivid global…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Ronghui Li , Hongwen Zhang , Yachao Zhang , Yuxiang Zhang , Youliang Zhang , Jie Guo , Yan Zhang , Xiu Li , Yebin Liu

3D conducting motion generation aims to synthesize fine-grained conductor motions from music, with broad potential in music education, virtual performance, digital human animation, and human-AI co-creation. However, this task remains…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Tianzhi Jia , Kaixing Yang , Xiaole Yang , Xulong Tang , Ke Qiu , Shikui Wei , Yao Zhao

In addition to traditional tasks such as prediction, classification and translation, deep learning is receiving growing attention as an approach for music generation, as witnessed by recent research groups such as Magenta at Google and CTRL…

声音 · 计算机科学 2018-11-13 Jean-Pierre Briot , François Pachet

The metaverse is expected to provide immersive entertainment, education, and business applications. However, virtual reality (VR) transmission over wireless networks is data- and computation-intensive, making it critical to introduce novel…

图像与视频处理 · 电气工程与系统科学 2024-01-03 Yiyu Guo , Zhijin Qin , Xiaoming Tao , Geoffrey Ye Li

Dance-to-music generation aims to generate music that is aligned with dance movements. Existing approaches typically rely on body motion features extracted from a single human dancer and limited dance-to-music datasets, which restrict their…

声音 · 计算机科学 2026-01-23 Jaekwon Im , Natalia Polouliakh , Taketo Akama

Controllable generation of 3D human motions becomes an important topic as the world embraces digital transformation. Existing works, though making promising progress with the advent of diffusion models, heavily rely on meticulously captured…

计算机视觉与模式识别 · 计算机科学 2024-01-25 Nhat M. Hoang , Kehong Gong , Chuan Guo , Michael Bi Mi

Synthesising appropriate choreographies from music remains an open problem. We introduce MDLT, a novel approach that frames the choreography generation problem as a translation task. Our method leverages an existing data set to learn to…

声音 · 计算机科学 2024-10-18 André Correia , Luís A. Alexandre

Video generation remains a challenging task due to spatiotemporal complexity and the requirement of synthesizing diverse motions with temporal consistency. Previous works attempt to generate videos in arbitrary lengths either in an…

计算机视觉与模式识别 · 计算机科学 2023-04-07 Xiaoqian Shen , Xiang Li , Mohamed Elhoseiny

Investigating the impact of fatigue on human physiological function and motor behavior is crucial for developing biomechanics and medical applications aimed at mitigating fatigue, reducing injury risk, and creating sophisticated ergonomic…

图形学 · 计算机科学 2026-04-14 Iliana Loi , Konstantinos Moustakas

Music-driven group choreography poses a considerable challenge but holds significant potential for a wide range of industrial applications. The ability to generate synchronized and visually appealing group dance motions that are aligned…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Nhat Le , Tuong Do , Khoa Do , Hien Nguyen , Erman Tjiputra , Quang D. Tran , Anh Nguyen