RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes
Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex scenes remains a persistent challenge. To address this, we propose RAD, a retrieval-augmented framework that approximates the benefits of multi-view stereo by utilizing retrieved neighbors as structural geometric proxies. Our method first employs an uncertainty-aware retrieval mechanism to identify low-confidence regions in the input and retrieve RGB-D context samples containing semantically similar content. We then process both the input and retrieved context via a dual-stream network and fuse them using a matched cross-attention module, which transfers geometric information only at reliable point correspondences. Evaluations on NYU Depth v2, KITTI, and Cityscapes demonstrate that RAD significantly outperforms state-of-the-art baselines on underrepresented classes, reducing relative absolute error by 29.2% on NYU Depth v2, 13.3% on KITTI, and 7.2% on Cityscapes, while maintaining competitive performance on standard in-domain benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationSimilar Papers 제목 키워드 기반
Self-Supervised Learning based Depth Estimation from Monocular Images
Depth Estimation has wide reaching applications in the field of Computer vision such as target tracking, augmented reality, and self-driving cars. The goal of Monocular Depth Estimation is to predict the depth map, given…
Depth EstimationMonocular Depth EstimationPose EstimationSelf-Driving Cars+2Monocular Depth Estimation with Augmented Ordinal Depth Relationships
Most existing algorithms for depth estimation from single monocular images need large quantities of metric groundtruth depths for supervised learning. We show that relative depth can be an informative cue for metric dept…
Depth EstimationDepth PredictionMonocular Depth EstimationStereo Matching+1MaskingDepth: 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+4Edge-aware Consistent Stereo Video Depth Estimation
Video depth estimation is crucial in various applications, such as scene reconstruction and augmented reality. In contrast to the naive method of estimating depths from images, a more sophisticated approach uses temporal…
Camera Pose EstimationDepth EstimationPose EstimationMetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning
Deep metric learning aims to learn features relying on the consistency or divergence of class labels. However, in monocular depth estimation, the absence of a natural definition of class poses challenges in the leveragin…
Depth EstimationMetric LearningMonocular Depth Estimation