Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking.
Longlong JingRuichi YuHenrik KretzschmarKang LiCharles R. QiHang ZhaoAlper AyvaciXu ChenDillon CowerYingwei LiYurong YouHan DengCongcong LiDragomir AnguelovPublished in: ICRA (2022)
Keyphrases
- depth estimation
- monocular images
- stereo vision
- depth map
- depth cues
- stereo matching
- scene understanding
- depth information
- partial occlusion
- stereo pair
- real scenes
- object detection
- object tracking
- dynamic scenes
- d objects
- image sequences
- depth estimates
- real time
- super resolution
- target object
- multiple objects
- disparity map
- particle filter
- multi view
- computer vision
- feature matching
- belief propagation
- stereo images
- video surveillance
- d scene
- high quality
- three dimensional