7 papers
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…
OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion
Tianyu Huang, Runnan Chen, Dongting Hu +3
Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to p…
ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes
Zhengqing Gao, Dongting Hu, Jia-Wang Bian +5
3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required, posing challenges for de…
Effective transport by 2D turbulence: Vortex-gas theory vs. scale-invariant inverse cascade
Julie Meunier, Basile Gallet
The scale-invariant inverse energy cascade is a hallmark of 2D turbulence, with its theoretical energy spectrum observed in both direct numerical simulations (DNS) and laboratory e…
MF-VITON: High-Fidelity Mask-Free Virtual Try-On with Minimal Input
Zhenchen Wan, Yanwu xu, Dongting Hu +6
Recent advancements in Virtual Try-On (VITON) have significantly improved image realism and garment detail preservation, driven by powerful text-to-image (T2I) diffusion models. Ho…
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…