ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2103.02396
27
18

S3S^3S3: Learnable Sparse Signal Superdensity for Guided Depth Estimation

3 March 2021
Yu-Kai Huang
Yueh-Cheng Liu
Tsung-Han Wu
Hung-Ting Su
Yu-Cheng Chang
T. Tsou
Yu-An Wang
Winston H. Hsu
    MDE
ArXivPDFHTML
Abstract

Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been leveraged as guidance for enhancing dense depth estimation, the improvement is limited due to its low density and imbalanced distribution. To maximize the utility from the sparse source, we propose S3S^3S3 technique, which expands the depth value from sparse cues while estimating the confidence of expanded region. The proposed S3S^3S3 can be applied to various guided depth estimation approaches and trained end-to-end at different stages, including input, cost volume and output. Extensive experiments demonstrate the effectiveness, robustness, and flexibility of the S3S^3S3 technique on LiDAR and Radar signal.

View on arXiv
Comments on this paper