Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation

About

We propose MAMo, a novel memory and attention frame-work for monocular video depth estimation. MAMo can augment and improve any single-image depth estimation networks into video depth estimation models, enabling them to take advantage of the temporal information to predict more accurate depth. In MAMo, we augment model with memory which aids the depth prediction as the model streams through the video. Specifically, the memory stores learned visual and displacement tokens of the previous time instances. This allows the depth network to cross-reference relevant features from the past when predicting depth on the current frame. We introduce a novel scheme to continuously update the memory, optimizing it to keep tokens that correspond with both the past and the present visual information. We adopt attention-based approach to process memory features where we first learn the spatio-temporal relation among the resultant visual and displacement memory tokens using self-attention module. Further, the output features of self-attention are aggregated with the current visual features through cross-attention. The cross-attended features are finally given to a decoder to predict depth on the current frame. Through extensive experiments on several benchmarks, including KITTI, NYU-Depth V2, and DDAD, we show that MAMo consistently improves monocular depth estimation networks and sets new state-of-the-art (SOTA) accuracy. Notably, our MAMo video depth estimation provides higher accuracy with lower latency, when omparing to SOTA cost-volume-based video depth models.

Rajeev Yasarla, Hong Cai, Jisoo Jeong, Yunxiao Shi, Risheek Garrepalli, Fatih Porikli• 2023

Related benchmarks

TaskDatasetResultRank
Monocular Depth EstimationKITTI (Eigen)
Abs Rel0.049
502
Depth EstimationKITTI (Eigen split)
RMSE1.884
276
Monocular Depth EstimationKITTI (Eigen split)
Abs Rel0.049
193
Monocular Depth EstimationDDAD (test)
RMSE10.462
122
Depth EstimationDDAD (val)
Sq Rel1.772
31
Video Depth EstimationKITTI (test)
Delta197.7
25
Video Depth EstimationNYUDV2 (Eigen split)
OPW Score0.388
15
Video Depth EstimationNYUDv2 (test)
delta191.9
12
Video Depth EstimationKITTI
rTC0.963
9
Monocular Video Depth EstimationNYU Video v2
Absolute Relative Error0.094
8
Showing 10 of 11 rows

Other info

Follow for update