English

Fractal Autoregressive Depth Estimation with Continuous Token Diffusion

Computer Vision and Pattern Recognition 2026-03-17 v1

Abstract

Monocular depth estimation can benefit from autoregressive (AR) generation, but direct AR modeling is hindered by the modality gap between RGB and depth, inefficient pixel-wise generation, and instability in continuous depth prediction. We propose a Fractal Visual Autoregressive Diffusion framework that reformulates depth estimation as a coarse-to-fine, next-scale autoregressive generation process. A VCFR module fuses multi-scale image features with current depth predictions to improve cross-modal conditioning, while a conditional denoising diffusion loss models depth distributions directly in continuous space and mitigates errors caused by discrete quantization. To improve computational efficiency, we organize the scale-wise generators into a fractal recursive architecture, reusing a base visual AR unit in a self-similar hierarchy. We further introduce an uncertainty-aware robust consensus aggregation scheme for multi-sample inference to improve fusion stability and provide a practical pixel-wise reliability estimate. Experiments on standard benchmarks demonstrate strong performance and validate the effectiveness of the proposed design.

Keywords

Cite

@article{arxiv.2603.14702,
  title  = {Fractal Autoregressive Depth Estimation with Continuous Token Diffusion},
  author = {Jinchang Zhang and Xinrou Kang and Guoyu Lu},
  journal= {arXiv preprint arXiv:2603.14702},
  year   = {2026}
}
R2 v1 2026-07-01T11:21:12.638Z