English

Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition

Computer Vision and Pattern Recognition 2022-12-06 v1

Abstract

Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to the convolution operations and the down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making our method 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps.

Keywords

Cite

@article{arxiv.2212.01538,
  title  = {Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition},
  author = {Yaqiao Dai and Renjiao Yi and Chenyang Zhu and Hongjun He and Kai Xu},
  journal= {arXiv preprint arXiv:2212.01538},
  year   = {2022}
}

Comments

19 pages (with supplementary material)

R2 v1 2026-06-28T07:21:04.340Z