Diffusion-Augmented Depth Prediction with Sparse Annotations
This work addresses depth estimation for autonomous driving with sparse annotations, representing an incremental improvement by integrating diffusion models into a supervised framework.
The paper tackles depth estimation in autonomous driving scenes with sparse annotations, where existing methods produce concave objects and overfit to valid pixels. The proposed Diffusion-Augmented Depth Prediction (DADP) framework achieves significant improvements in depth structures and robustness on three driving benchmarks.
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.