Multi-frame self-supervised depth with transformers
Multi-frame depth estimation improves over single-frame approaches by also leveraging
geometric relationships between images via feature matching, in addition to learning …
geometric relationships between images via feature matching, in addition to learning …
Self-supervised monocular depth estimation for gastrointestinal endoscopy
Y Liu, S Zuo - Computer Methods and Programs in Biomedicine, 2023 - Elsevier
Background and objective: Gastrointestinal (GI) endoscopy represents a promising tool for
GI cancer screening. However, the limited field of view and uneven skills of endoscopists …
GI cancer screening. However, the limited field of view and uneven skills of endoscopists …
Learning optical flow, depth, and scene flow without real-world labels
Self-supervised monocular depth estimation enables robots to learn 3D perception from raw
video streams. This scalable approach leverages projective geometry and ego-motion to …
video streams. This scalable approach leverages projective geometry and ego-motion to …
Deep geometry-aware camera self-calibration from video
Accurate intrinsic calibration is essential for camera-based 3D perception, yet, it typically
requires targets of well-known geometry. Here, we propose a camera self-calibration …
requires targets of well-known geometry. Here, we propose a camera self-calibration …
Cameras as rays: Pose estimation via ray diffusion
Estimating camera poses is a fundamental task for 3D reconstruction and remains
challenging given sparsely sampled views (< 10). In contrast to existing approaches that …
challenging given sparsely sampled views (< 10). In contrast to existing approaches that …
Attentive and contrastive learning for joint depth and motion field estimation
Estimating the motion of the camera together with the 3D structure of the scene from a
monocular vision system is a complex task that often relies on the so-called scene rigidity …
monocular vision system is a complex task that often relies on the so-called scene rigidity …
Geometric unsupervised domain adaptation for semantic segmentation
Simulators can efficiently generate large amounts of labeled synthetic data with perfect
supervision for hard-to-label tasks like semantic segmentation. However, they introduce a …
supervision for hard-to-label tasks like semantic segmentation. However, they introduce a …
Full surround monodepth from multiple cameras
Self-supervised monocular depth and ego-motion estimation is a promising approach to
replace or supplement expensive depth sensors such as LiDAR for robotics applications like …
replace or supplement expensive depth sensors such as LiDAR for robotics applications like …
Depth field networks for generalizable multi-view scene representation
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping
image data to classical structures such as cost volumes or epipolar constraints to improve …
image data to classical structures such as cost volumes or epipolar constraints to improve …
DualRefine: Self-supervised depth and pose estimation through iterative epipolar sampling and refinement toward equilibrium
A Bangunharcana, A Magd… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Self-supervised multi-frame depth estimation achieves high accuracy by computing
matching costs of pixel correspondences between adjacent frames, injecting geometric …
matching costs of pixel correspondences between adjacent frames, injecting geometric …