learning approaches to estimate depth from rgb
play

Learning Approaches to Estimate Depth from RGB Lecture 5 What will - PowerPoint PPT Presentation

Learning Approaches to Estimate Depth from RGB Lecture 5 What will we learn - Latest Approaches to Depth Estimation based on Machine Learning (DNNs) Why do we need new approaches? Paper1 -> CNNs for Depth estimation Paper2


  1. Learning Approaches to Estimate Depth from RGB Lecture 5

  2. What will we learn - Latest Approaches to Depth Estimation based on Machine Learning (DNNs) Why do we need new approaches? ● Paper1 -> CNNs for Depth estimation ● ● Paper2 -> Semantics for Depth Estimation ● Paper3 -> Differentiable Rendering for Depth Estimation ● Paper4 and Paper5 -> Learned Multi-view geometry

  3. Courtesy figure: Silvio Savarese.

  4. Meta - What is important in DNN research? Priors Architecture + Data Loss

  5. Eigen et al., “Depth Map Prediction from a Single Image using a Multi-Scale Deep Network”, NeurIPS14

  6. Eigen et al.

  7. Tatarchenko et al. “What Do Single-view 3D Reconstruction Networks Learn?”, CVPR19

  8. Kato et al. - “Neural 3D Mesh Renderer”, CVPR18

  9. Rendering 3D model + Parameters

  10. Kato et al. - “Neural 3D Mesh Renderer”, CVPR18

  11. Godard et al. - “Unsupervised Monocular Depth Estimation with Left-Right Consistency”, CVPR17

  12. Zhang et al. - LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery, arxiv

  13. Question - What are Latest Trends in Learning Depth from RGB?

  14. What are Latest Trends in Learning Depth from RGB? 1. Large amount of data + Powerful parametric function approximators (DNNs) 2. Exploit semantics 3. Differentiable Rendering 4. Self supervision from stereo 5. Sparse supervision from Lidar

Recommend


More recommend