SOURCE-LINKED INTELLIGENCE

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

This work presents $\textbf{Lapis}$, a $\textbf{l}$inear-$\textbf{a}$ttention-based $\textbf{pi}$xel-$\textbf{s}$pace generative framework that achieves efficient and high-fidelity depth estimation with one-step diffusion. While generative frameworks have significantly advanced monocular depth estimation with superior detail fidelity, the $\mathcal{O}(N^2)$ complexity of standard attention and the multi-step denoising process introduce prohibitive computational costs when scaling them to high-resolution image applications. Although linear attention and one-step prediction are intuitively viabl

Read original source ↗ Open in workspace

recordType

paper

region

Global