Diffusion-Augmented Depth Prediction with Sparse Annotations

Abstract

Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity of annotations makes the task challenging. Supervised models produce concave objects due to insufficient structural information. They overfit to valid pixels and fail to restore spatial structures. Self-supervised methods are proposed for the problem. Their robustness is limited by pose estimation, leading to erroneous results in natural scenes. In this paper, we propose a supervised framework termed Diffusion-Augmented Depth Prediction (DADP). We leverage the structural characteristics of diffusion model to enforce depth structures of depth models in a plug-and-play manner. An object-guided integrality loss is also proposed to further enhance regional structure integrality by fetching objective information. We evaluate DADP on three driving benchmarks and achieve significant improvements in depth structures and robustness. Our work provides a new perspective on depth estimation with sparse annotations in autonomous driving scenes.

Accepted by ACM MM'2023

References in corpus (7)

• Diffusion Models Beat GANs on Image Synthesis
• Score-Based Generative Modeling through Stochastic Differential Equations
• Classifier-Free Diffusion Guidance
• Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
• Diffusion Models for Implicit Image Segmentation Ensembles
• Less is More: Consistent Video Depth Estimation with Masked Frames Modeling
• Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation