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.
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.· ACM Transactions on Graphics· 4 citations· ⚡2
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
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
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· Computer Vision and Pattern...· 2 citations
PXDepth is a discriminative monocular depth model that separates global context modeling from pixel-level depth prediction, and combines faithful local geometry with competitive global depth accuracy while remaining efficient at inference.
Zhi-Yuan Yuan, Guanying Chen, Lingteng Qiu et al.· 1 citation
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.· The Visual Computer· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.