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

• URL: http://arxiv.org/abs/2607.12433v1
• Date: Tue, 14 Jul 2026 07:06:46 GMT
• Title: ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning
• Abstract summary: Diffusion models assume that depth can be recovered as a globally smooth field through iterative denoising.<n>We introduce ARDepth, which formulates depth estimation as structured auto-regressive generation.<n>We show that our approach achieves strong performance and produces structurally consistent depth predictions across scales.
• Score: 66.42476564611607
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth [11.871264497562008]
  We propose a novel framework that transfers the scale-aware geometric priors of multi-view models into monocular depth foundation models.<n>Specifically, we introduce an Epipolar Distillation (EpiDistill), which enables the single-view prediction model to retain epipolar attention patterns and maintain geometric consistency without requiring multi-view inputs at inference.
  arXiv  Detail & Related papers  (2026-07-17T03:49:14Z)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• Any to Full: Prompting Depth Anything for Depth Completion in One Stage [23.09070498141459]
  Existing RGBD-fused depth completion methods learn priors jointly conditioned on training RGB distribution and specific depth patterns.<n>Recent efforts leverage monocular depth estimation models to introduce domain-general geometric priors.<n>We present Any2Full, a one-stage, domain-general, and pattern-agnostic framework that reformulates completion as a scale-prompting adaptation of a pretrained MDE model.
  arXiv  Detail & Related papers  (2026-03-05T22:08:40Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction [2.8012387812933035]
  Splat is an active reconstruction framework that reconstructs objects with both appearance and accurate geometry.<n>Splat produces physically consistent completeness within minutes, achieving superior reconstruction fidelity and surface completeness compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-01-11T17:14:33Z)
• GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding [14.436063587920005]
  We introduce GeoDiT, the first diffusion-based vision-language model tailored for the geospatial domain.<n>It achieves significant gains in image captioning, visual grounding, and multi-object detection.<n>Our work validates that aligning the generative process with the data's intrinsic structure is key to unlocking superior performance in complex geospatial analysis.
  arXiv  Detail & Related papers  (2025-12-02T07:59:46Z)
• PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction [87.33016661440202]
  Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality.<n>We propose PointNSP, a coarse-to-fine generative framework that preserves global shape structure at low resolutions.<n> Experiments on ShapeNet show that PointNSP establishes state-of-the-art (SOTA) generation quality for the first time within the autoregressive paradigm.
  arXiv  Detail & Related papers  (2025-10-07T06:31:02Z)
• DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion [59.25479674775212]
  DepR is a depth-guided single-view scene reconstruction framework.<n>It generates individual objects and composes them into a coherent 3D layout.<n>It achieves state-of-the-art performance despite being trained on limited synthetic data.
  arXiv  Detail & Related papers  (2025-07-30T16:40:46Z)
• PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency [63.74016242995453]
  PacGDC is a label-efficient technique that enhances data diversity with minimal annotation effort for generalizable depth completion.<n>We propose a new data synthesis pipeline that uses multiple depth foundation models as scale manipulators.<n>Experiments show that PacGDC achieves remarkable generalizability across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-07-10T01:56:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.