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.

arXiv commentAccepted by ACM MM'2023

References in corpus (17)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Decoupled Weight Decay Regularization
• Denoising Diffusion Probabilistic Models
• Diffusion Models Beat GANs on Image Synthesis
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• Score-Based Generative Modeling through Stochastic Differential Equations
• Classifier-Free Diffusion Guidance
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• Progressive Distillation for Fast Sampling of Diffusion Models
• Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
• Diffusion Models for Implicit Image Segmentation Ensembles
• NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
• Less is More: Consistent Video Depth Estimation with Masked Frames Modeling
• Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation
• SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
• PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes
• NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation