6 papers
MaskControl: Spatio-Temporal Control for Masked Motion Synthesis
Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Korrawe Karunratanakul +7
Recent advances in motion diffusion models have enabled spatially controllable text-to-motion generation. However, these models struggle to achieve high-precision control while mai…
GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement
Peiye Zhuang, Songfang Han, Chaoyang Wang +7
We propose a novel approach for 3D mesh reconstruction from multi-view images. Our method takes inspiration from large reconstruction models like LRM that use a transformer-based t…
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
Yushu Wu, Zhixing Zhang, Yanyu Li +11
We have witnessed the unprecedented success of diffusion-based video generation over the past year. Recently proposed models from the community have wielded the power to generate c…
Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
Tanzila Rahman, Shweta Mahajan, Hsin-Ying Lee +3
Text-to-image (TTI) diffusion models have demonstrated impressive results in generating high-resolution images of complex and imaginative scenes. Recent approaches have further ext…
Taming Data and Transformers for Audio Generation
Moayed Haji-Ali, Willi Menapace, Aliaksandr Siarohin +2
The scalability of ambient sound generators is hindered by data scarcity, insufficient caption quality, and limited scalability in model architecture. This work addresses these cha…
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Dongting Hu, Jierun Chen, Xijie Huang +16
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…