Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior (2312.10118v1)

Published 15 Dec 2023 in cs.CV

Abstract: Self-supervised monocular depth estimation (DE) is an approach to learning depth without costly depth ground truths. However, it often struggles with moving objects that violate the static scene assumption during training. To address this issue, we introduce a coarse-to-fine training strategy leveraging the ground contacting prior based on the observation that most moving objects in outdoor scenes contact the ground. In the coarse training stage, we exclude the objects in dynamic classes from the reprojection loss calculation to avoid inaccurate depth learning. To provide precise supervision on the depth of the objects, we present a novel Ground-contacting-prior Disparity Smoothness Loss (GDS-Loss) that encourages a DE network to align the depth of the objects with their ground-contacting points. Subsequently, in the fine training stage, we refine the DE network to learn the detailed depth of the objects from the reprojection loss, while ensuring accurate DE on the moving object regions by employing our regularization loss with a cost-volume-based weighting factor. Our overall coarse-to-fine training strategy can easily be integrated with existing DE methods without any modifications, significantly enhancing DE performance on challenging Cityscapes and KITTI datasets, especially in the moving object regions.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Jaeho Moon (5 papers)
  2. Juan Luis Gonzalez Bello (12 papers)
  3. Byeongjun Kwon (3 papers)
  4. Munchurl Kim (52 papers)
Citations (1)

Summary

We haven't generated a summary for this paper yet.

Youtube Logo Streamline Icon: https://streamlinehq.com