LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning
Advances in neural networks enable tackling complex computer vision tasks such as depth estimation of outdoor scenes at unprecedented accuracy. Promising research has been done on depth estimation. However, current efforts are computationally resource-intensive and do not consider the resource constraints of autonomous devices, such as robots and drones. In this work, we present a fast and battery-efficient approach for depth estimation. Our approach devises model-agnostic curriculum-based learning for depth estimation. Our experiments show that the accuracy of our model performs on par with the state-of-the-art models, while its response time outperforms other models by 71%. All codes are available online at https://github.com/fatemehkarimii/LightDepth.
Code (1)
Tasks
Depth EstimationMonocular Depth EstimationSimilar Papers 제목 키워드 기반
LightDepth: Single-View Depth Self-Supervision from Illumination Decline
Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in the case of endoscopies, where such dat…
Depth Estimation3D Densification for Multi-Map Monocular VSLAM in Endoscopy
Multi-map Sparse Monocular visual Simultaneous Localization and Mapping applied to monocular endoscopic sequences has proven efficient to robustly recover tracking after the frequent losses in endoscopy due to motion blu…
Camera LocalizationDepth EstimationMonocular Depth EstimationSimultaneous Localization and MappingIntrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces
Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning as it estimates depth without requiring ground truth depth maps. This approach typically uses a photometric consistenc…
Depth EstimationDepth PredictionIntrinsic Image DecompositionKnowledge Distillation+1Uni6Dv2: Noise Elimination for 6D Pose Estimation
Uni6D is the first 6D pose estimation approach to employ a unified backbone network to extract features from both RGB and depth images. We discover that the principal reasons of Uni6D performance limitations are Instance…
6D Pose EstimationDenoisingInstance SegmentationPose Estimation+1Subspace Tracking under Dynamic Dimensionality for Online Background Subtraction
Long-term modeling of background motion in videos is an important and challenging problem used in numerous applications such as segmentation and event recognition. A major challenge in modeling the background from point …