Skip to content

ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning

Jul 2026 · arXiv.org · Vol abs/2607.12433 · 0 citations · 59 references
Computer Science

TL;DR

This work introduces ARDepth, which formulates depth estimation as structured auto-regressive generation, and produces structurally consistent depth predictions across scales, validating auto-regressive generation as a promising alternative paradigm for geometric modeling.

Abstract

Diffusion models have recently 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.

View source

Similar papers

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Marigold V2 achieves state-of-the-art results when applied to other dense regression tasks, such as surface normals estimation and intrinsic image decomposition, and achieves state-of-the-art results when applied to other dense regression tasks, such as surface normals estimation and intrinsic image decomposition.

Igor Pavlovic, Thiemo Wandel, Anton Obukhov et al. · 4 citations · ⚡2
Preprint Aug 2026

M2Depth: Unifying Monocular Depth Foundation Priors with Multi-View Stereo

This work proposes a novel framework that overcomes this limitation by tightly coupling a DFM with a cascade MVS pipeline through a bidirectional mutual refinement strategy, and introduces a prior-guided cost volume refinement mechanism that effectively integrates multi-view and monocular information via attention-base...

Byeonggwon Lee, Sanggil Lee, Si-Woo Lee et al. · 0 citations
Preprint Oct 2026

EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder

Recovering detailed geometry from high-resolution images is critical for precise perception of the surroundings and objects. However, existing methods which use latent-space modeling and VAE reconstruction can compromise geometric details. Furthermore, decoding from latent codes introduces substantial inference overhea...

Bo-Wen Chai, Tian-Bao Zhang, Shu-Yu Wu et al. · 0 citations
Conference Oct 2026

Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation

This paper proposes HypoDepth, the first event-image monocular depth iterative refinement framework, which outperforms existing approaches on DSEC and MVSEC with state-of-the-art results and strong zero-shot generalization.

Dai-Kun Liu, Teng Wang, Chang-Yin Sun · 2 citations
Sep 2026

Self-supervised monocular depth estimation using dynamic self-distillation and asymptotic bidirectional feature aggregation

This paper introduces dynamic self-distillation (DSD) to provide additional supervision during training, enhancing the model’s ability to learn fine-grained geometric representations, and designs the asymptotic bidirectional feature aggregation network (ABFANet), which enhances multi-scale features through progressive...

Xiao-Gang Song, Jian Liu, Qin Zhao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.