Monocular Depth Estimation Using Whole Strip Masking and Reliability-Based Refinement
We propose a monocular depth estimation algorithm, which extracts a depth map from a single image, based on whole strip masking (WSM) and reliability-based refinement. First, we develop a convolutional neural network (CNN) tailored for the depth estimation. Specifically, we design a novel filter, called WSM, to exploit the tendency that a scene has similar depths in horizonal or vertical directions. The proposed CNN combines WSM upsampling blocks with the ResNet encoder. Second, we measure the reliability of an estimated depth, by appending additional layers to the main CNN. Using the reliability information, we perform conditional random field (CRF) optimization to refine the estimated depth map. Extensive experimental results demonstrate that the proposed algorithm provides the state-of-the-art depth estimation performance, outperforming conventional algorithms significantly.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationMonocular Depth EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation
We propose MaskingDepth, a novel semi-supervised learning framework for monocular depth estimation to mitigate the reliance on large ground-truth depth quantities. MaskingDepth is designed to enforce consistency between …
Data AugmentationDepth EstimationDomain AdaptationImage Classification+4Image Masking for Robust Self-Supervised Monocular Depth Estimation
Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to predict accurate pixel-wise depth witho…
Autonomous DrivingDepth EstimationMonocular Depth EstimationMotion Estimation+1Variational Monocular Depth Estimation for Reliability Prediction
Self-supervised learning for monocular depth estimation is widely investigated as an alternative to supervised learning approach, that requires a lot of ground truths. Previous works have successfully improved the accura…
Autonomous VehiclesDepth EstimationMonocular Depth EstimationPrediction+1MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentation
Depth-aware video panoptic segmentation tackles the inverse projection problem of restoring panoptic 3D point clouds from video sequences, where the 3D points are augmented with semantic classes and temporally consistent…
Depth-aware Video Panoptic SegmentationDepth EstimationDepth PredictionImage Segmentation+5MGNiceNet: Unified Monocular Geometric Scene Understanding
Monocular geometric scene understanding combines panoptic segmentation and self-supervised depth estimation, focusing on real-time application in autonomous vehicles. We introduce MGNiceNet, a unified approach that uses …
Autonomous DrivingAutonomous VehiclesDepth EstimationDepth Prediction+5