Robust Depth Super-Resolution via Adaptive Diffusion Sampling

TL;DR

AdaDS introduces an adaptive diffusion sampling framework for robust depth super-resolution, effectively recovering high-resolution depth maps from degraded inputs by leveraging Gaussian smoothing properties and uncertainty-based sampling.

Contribution

It presents a novel adaptive diffusion sampling method that enhances robustness and generalization in depth super-resolution from degraded inputs.

Findings

Outperforms state-of-the-art methods on real-world benchmarks.

Demonstrates strong zero-shot generalization capabilities.

Shows resilience to various degradation patterns.

Abstract

We propose AdaDS, a generalizable framework for depth super-resolution that robustly recovers high-resolution depth maps from arbitrarily degraded low-resolution inputs. Unlike conventional approaches that directly regress depth values and often exhibit artifacts under severe or unknown degradation, AdaDS capitalizes on the contraction property of Gaussian smoothing: as noise accumulates in the forward process, distributional discrepancies between degraded inputs and their pristine high-quality counterparts diminish, ultimately converging to isotropic Gaussian prior. Leveraging this, AdaDS adaptively selects a starting timestep in the reverse diffusion trajectory based on estimated refinement uncertainty, and subsequently injects tailored noise to position the intermediate sample within the high-probability region of the target posterior distribution. This strategy ensures inherent robustness, enabling generative prior of a pre-trained diffusion model to dominate recovery even when upstream estimations are imperfect. Extensive experiments on real-world and synthetic benchmarks demonstrate AdaDS's superior zero-shot generalization and resilience to diverse degradation patterns compared to state-of-the-art methods.