NeFut Logo NeFut
Admin Login

[CS.AI] ARDepth: A Breakthrough in Auto-regressive Monocular Depth Estimation

Published at: 2026-07-16 22:00 Last updated: 2026-07-17 08:45
#algorithm #AI #Machine Learning

Abstract

Recently, diffusion models have become the dominant paradigm for monocular depth estimation (MDE). However, they implicitly assume that depth can be recovered as a globally smooth field through iterative denoising, which does not explicitly reflect the piecewise and scale-dependent organization of scene geometry.

In practice, geometric structure emerges progressively across spatial scales, where coarse layout, surfaces, and boundaries are constructed in a hierarchical manner.

Motivated by this observation, we introduce ARDepth, which formulates depth estimation as structured auto-regressive generation. Instead of recovering depth through global refinement, ARDepth progressively constructs depth representations as spatial resolution increases.

To support this generative process, we introduce Scale-Progressive Conditioning (SPC) to inject multi-scale visual features at each generation stage, and Semantic-Aware Guidance (SAG) to provide scene-level semantic priors that enhance global structural consistency.

Together, these designs enable the model to capture fine-grained local details while maintaining coherent global geometry. Empirical results demonstrate that our approach achieves strong performance and produces structurally consistent depth predictions across scales, validating auto-regressive generation as a promising alternative paradigm for geometric modeling.

Blogger's Review: ARDepth effectively balances capturing local details and maintaining global structure through its progressive generation and multi-scale conditioning. This auto-regressive method not only enhances depth estimation accuracy but also offers a fresh perspective for future geometric modeling, warranting exploration in broader applications.

Original Source: https://arxiv.org/abs/2607.12433

[h] Back to Home