DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation

TL;DR

DiffusionDepth introduces a novel diffusion-based method for monocular depth estimation, reformulating the task as a denoising process in latent space to improve accuracy and detail over existing approaches.

Contribution

It proposes a self-diffusion framework that enhances depth estimation by iterative denoising, overcoming challenges of sparse ground truth data and achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on KITTI and NYU-Depth-V2 datasets.

Refines depth maps step-by-step for higher accuracy and detail.

Operates efficiently with acceptable inference times.

Abstract

Monocular depth estimation is a challenging task that predicts the pixel-wise depth from a single 2D image. Current methods typically model this problem as a regression or classification task. We propose DiffusionDepth, a new approach that reformulates monocular depth estimation as a denoising diffusion process. It learns an iterative denoising process to `denoise' random depth distribution into a depth map with the guidance of monocular visual conditions. The process is performed in the latent space encoded by a dedicated depth encoder and decoder. Instead of diffusing ground truth (GT) depth, the model learns to reverse the process of diffusing the refined depth of itself into random depth distribution. This self-diffusion formulation overcomes the difficulty of applying generative models to sparse GT depth scenarios. The proposed approach benefits this task by refining depth estimation step by step, which is superior for generating accurate and highly detailed depth maps. Experimental results on KITTI and NYU-Depth-V2 datasets suggest that a simple yet efficient diffusion approach could reach state-of-the-art performance in both indoor and outdoor scenarios with acceptable inference time.