エッジデバイス向け多段階ガイド拡散による画像復元：身体性AIにおける軽量知覚に向けて
Multi-Step Guided Diffusion for Image Restoration on Edge Devices: Toward Lightweight Perception in Embodied AI
拡散モデルの各ノイズ除去ステップで勾配更新を多段階化し、Jetson Orin Nano上で超解像やデブラリングの品質と汎化性能を低遅延で向上させる手法を提案。
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Diffusion models have shown remarkable flexibility for solving inverse problems without task-specific retraining. However, existing approaches such as Manifold Preserving Guided Diffusion (MPGD) apply only a single gradient update per denoising step, limiting restoration fidelity and robustness, especially in embedded or out-of-distribution settings. In this work, we introduce a multistep optimization strategy within each denoising timestep, significantly enhancing image quality, perceptual accuracy, and generalization. Our experiments on super-resolution and Gaussian deblurring demonstrate that increasing the number of gradient updates per step improves LPIPS and PSNR with minimal latency overhead. Notably, we validate this approach on a Jetson Orin Nano using degraded ImageNet and a UAV dataset, showing that MPGD, originally trained on face datasets, generalizes effectively to natural and aerial scenes. Our findings highlight MPGD's potential as a lightweight, plug-and-play restoration module for real-time visual perception in embodied AI agents such as drones and mobile robots.