Multi-Loss Rebalancing Algorithm for Monocular Depth Estimation
An algorithm to combine multiple loss terms adaptively for training a monocular depth estimator is proposed in this work. We construct a loss function space containing tens of losses. Using more losses can improve inference capability without any additional complexity in the test phase. However, when many losses are used, some of them may be neglected during training. Also, since each loss decreases at a different speed, adaptive weighting is required to balance the contributions of the losses. To address these issues, we propose the loss rebalancing algorithm that initializes and rebalances the weight for each loss function adaptively in the course of training. Experimental results show that the proposed algorithm provides state-of-the-art depth estimation results on various datasets. Codes are available at https://github.com/jaehanlee-mcl/multi-loss-rebalancing-depth.
Code (1)
Tasks
Depth EstimationMonocular Depth EstimationSimilar Papers 제목 키워드 기반
Real-time Monocular Depth Estimation with Sparse Supervision on Mobile
Monocular (relative or metric) depth estimation is a critical task for various applications, such as autonomous vehicles, augmented reality and image editing. In recent years, with the increasing availability of mobile d…
Autonomous VehiclesDepth EstimationGPUKnowledge Distillation+2MDS-Net: A Multi-scale Depth Stratification Based Monocular 3D Object Detection Algorithm
Monocular 3D object detection is very challenging in autonomous driving due to the lack of depth information. This paper proposes a one-stage monocular 3D object detection algorithm based on multi-scale depth stratificat…
3D Object DetectionAutonomous DrivingDepth EstimationDepth Prediction+4A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation
This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. A cycled generative adversarial network is designed to obtain high-quality self-supervise…
Depth EstimationGenerative Adversarial NetworkMonocular Visual OdometryMulti-Task Learning+2SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments
We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences wit…
Depth CompletionAnalysis of NaN Divergence in Training Monocular Depth Estimation Model
The latest advances in deep learning have facilitated the development of highly accurate monocular depth estimation models. However, when training a monocular depth estimation network, practitioners and researchers have …
Depth EstimationMonocular Depth Estimation