高效高分辨率图像编辑：基于幻觉感知损失与自适应分块
Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
AI总结：
MobilePicasso通过幻觉感知损失、潜在投影和自适应分块，在移动设备上实现高效4K图像编辑，质量提升18-48%，幻觉减少14-51%，延迟降低55.8倍。
摘要：
高分辨率（4K）图像到图像的合成对于移动应用而言已变得日益重要。现有的用于图像编辑的扩散模型在资源受限设备上部署时，在内存和图像质量方面面临重大挑战。在本文中，我们提出了MobilePicasso，一个新颖的系统，能够在高分辨率下实现高效的图像编辑，同时最小化计算成本和内存占用。MobilePicasso包含三个阶段：（i）使用幻觉感知损失在标准分辨率下执行图像编辑，（ii）应用潜在投影以避免进入像素空间，（iii）使用自适应上下文保持分块将编辑后的图像潜在表示上采样到更高分辨率。我们进行的包含46名参与者的用户研究表明，与现有方法相比，MobilePicasso不仅将图像质量提升了18%至48%，还将幻觉减少了14%至51%。MobilePicasso展现出显著更低的延迟，例如高达55.8倍的加速，而运行时内存仅小幅增加，例如相比先前工作仅增加9%。令人惊讶的是，观察到MobilePicasso在设备上的运行时间比在A100 GPU上运行的基于服务器的高分辨率图像编辑模型还要快。
英文摘要：
High-resolution (4K) image-to-image synthesis has become increasingly important for mobile applications. Existing diffusion models for image editing face significant challenges, in terms of memory and image quality, when deployed on resource-constrained devices. In this paper, we present MobilePicasso, a novel system that enables efficient image editing at high resolutions, while minimising computational cost and memory usage. MobilePicasso comprises three stages: (i) performing image editing at a standard resolution with hallucination-aware loss, (ii) applying latent projection to overcome going to the pixel space, and (iii) upscaling the edited image latent to a higher resolution with adaptive context-preserving tiling. Our user study with 46 participants reveals that MobilePicasso not only improves image quality by 18-48% but reduces hallucinations by 14-51% over existing methods. MobilePicasso demonstrates significantly lower latency, e.g., up to 55.8$\times$ speed-up, yet with a small increase in runtime memory, e.g., a mere 9% increase over prior work. Surprisingly, the on-device runtime of MobilePicasso is observed to be faster than a server-based high-resolution image editing model running on an A100 GPU.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
