8 papers
EgoPlay: Event-Triggered Video Editing for Egocentric Streams
Jinjie Mai, Gordon Guocheng Qian, Willi Menapace +8
We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data buil…
S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
Lin Zhao, Yushu Wu, Aleksei Lebedev +11
Diffusion Transformers (DiTs) have recently improved video generation quality. However, their heavy computational cost makes real-time or on-device generation infeasible. In this w…
SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
Dongting Hu, Aarush Gupta, Magzhan Gabidolla +12
Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and mem…
EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing
Runjia Li, Moayed Haji-Ali, Ashkan Mirzaei +9
We study instruction-guided editing of egocentric videos for interactive AR applications. While recent AI video editors perform well on third-person footage, egocentric views prese…
CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas
Gordon Guocheng Qian, Ruihang Zhang, Tsai-Shien Chen +11
Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we pr…
Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds
Yushu Wu, Yanyu Li, Anil Kag +9
Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like…
Improving Progressive Generation with Decomposable Flow Matching
Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov +4
Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fin…
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…