SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing
Not on the map. Why?
Abstract (arXiv)
Most monocular depth sensing methods use conventionally captured images that are created without considering scene content. In contrast, animal eyes have fast mechanical motions, called saccades, that control how the scene is imaged by the fovea, where resolution is highest. In this paper, we present the SaccadeCam framework for adaptively distributing resolution onto regions of interest in the scene. Our algorithm for adaptive resolution is a self-supervised network and we demonstrate results for end-to-end learning for monocular depth estimation. We also show preliminary results with a real SaccadeCam hardware prototype.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 72 references that are in the map. First posted on arXiv 24 Mar 2021.
Builds on
25 of 72 references.
References · 25
- 2017Attention Is All You Needcited by 59,932
- 2019Stand-Alone Self-Attention in Vision Modelscited by 542
- 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
- 2017Sparsity Invariant CNNscited by 325
- 2015DRAW: A Recurrent Neural Network For Image Generationcited by 190
- 2016Single-Image Depth Perception in the Wildcited by 179
- 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
- 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
- 2019Zoom To Learn, Learn To Zoomcited by 114
- 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
- 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
- 2019Neural RGB->D Sensing: Depth and Uncertainty from a Video Cameracited by 69
13 more
- 2019Deep Optics for Monocular Depth Estimation and 3D Object Detectioncited by 65
- 2019Deep Optics for Single-shot High-dynamic-range Imagingcited by 62
- 2019Learning Single Camera Depth Estimation using Dual-Pixelscited by 49
- 2020Learning When and Where to Zoom with Deep Reinforcement Learningcited by 43
- 2016Learning Sensor Multiplexing Design through Back-propagationcited by 28
- 2018Estimating Depth from RGB and Sparse Sensingcited by 23
- 2019Gated2Depth: Real-time Dense Lidar from Gated Imagescited by 23
- 2016ATGV-Net: Accurate Depth Super-Resolutioncited by 22
- 2019Efficient Object Detection in Large Images using Deep Reinforcement Learningcited by 21
- 2020Polka Lines: Learning Structured Illumination and Reconstruction for Active Stereocited by 21
- 2019LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Imagescited by 12
- 2017Hierarchical Attentive Recurrent Trackingcited by 7
- 2015RATM: Recurrent Attentive Tracking Modelcited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.