论文精选

量子启发可训练的图像补全模型发布

Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting

精选理由

这个模型用到了量子计算的思路,能更高效地处理图像补全任务,比传统方法更省参数。

这篇论文提出了一种基于量子启发张量网络的图像补全方法,其核心是可逆的对角量子傅里叶变换(QFT)松弛结构,计算复杂度为O(N²logN),能高效学习图像补全变换。该方法通过无约束的梯度优化实现快速训练,在随机采样数据上表现优于固定变换和单图优化,参数量远少于大型单元架构。

原文 · arXiv cs.LG

Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting

This work introduces quantum-inspired tensor-network circuits as trainable transforms for image inpainting. Among the proposed architectures, the diagonal quantum Fourier transform (QFT) relaxation is invertible with $O(N^2 \log N)$ computational cost for $N\times N$ images, inherently preserving minimum coherence throughout training via its circuit structure and eliminating the need for explicit coherence penalties. Unconstrained gradient-based phase optimization (Riemannian-optimization free) enables efficient learning from randomly sampled training data, allowing the learned transform to generalize to test images observed through fixed sampling masks. Numerical tests show that the learned models outperform fixed transforms and per-image optimization while matching the performance of much larger unitary architectures, yet with far fewer parameters.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks、图像补全、张量网络,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Shiwen An, Konstantinos Slavakis),经 AITOP 多维评分管线结构化提炼。