Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2026

Abstract

We propose AdaDS, an Adaptive Diffusion Sampling framework for prompted metric depth estimation, which estimates high-resolution metric depth from an image and an arbitrarily degraded low-resolution depth prompt. This setting is commonly studied as depth super-resolution, where existing methods typically regress depth directly without an explicit prior over high-quality depth, and thus often produce artifacts under severe or unseen degradations. In contrast, AdaDS exploits the contraction property of Gaussian smoothing: as noise accumulates in the forward diffusion process, the noisy distributions of degraded prompts and their high-quality counterparts converge toward an isotropic Gaussian prior, while the prompt content is gradually erased. Accordingly, AdaDS refines the prompt and estimates its uncertainty to adaptively select a starting timestep, and injects learned noise to place the intermediate sample in a high-density region of the depth distribution learned by a pre-trained diffusion model. Denoising from this sample yields high-quality depth with fine-grained details and corrects residual errors, even under imperfect prompt refinement. Experiments on real-world and synthetic benchmarks demonstrate its superior zero-shot generalization and robustness to diverse degradations. Code is available at https://github.com/w2kun/AdaDS.

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Publication

Proceedings of the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS 2026), Sydney, Australia, December 6-12

First Page

1

Last Page

20

City or Country

Sydney,Australia

Additional URL

https://neurips.cc/virtual/2026/poster/153483

Download

Share

COinS