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

FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion

About

Depth completion aims to recover a dense depth map from a sparse depth map with the corresponding color image as input. Recent approaches mainly formulate depth completion as a one-stage end-to-end learning task, which outputs dense depth maps directly. However, the feature extraction and supervision in one-stage frameworks are insufficient, limiting the performance of these approaches. To address this problem, we propose a novel end-to-end residual learning framework, which formulates the depth completion as a two-stage learning task, i.e., a sparse-to-coarse stage and a coarse-to-fine stage. First, a coarse dense depth map is obtained by a simple CNN framework. Then, a refined depth map is further obtained using a residual learning strategy in the coarse-to-fine stage with a coarse depth map and color image as input. Specially, in the coarse-to-fine stage, a channel shuffle extraction operation is utilized to extract more representative features from the color image and coarse depth map, and an energy based fusion operation is exploited to effectively fuse these features obtained by channel shuffle operation, thus leading to more accurate and refined depth maps. We achieve SoTA performance in RMSE on KITTI benchmark. Extensive experiments on other datasets future demonstrate the superiority of our approach over current state-of-the-art depth completion approaches.

Lina Liu, Xibin Song, Xiaoyang Lyu, Junwei Diao, Mengmeng Wang, Yong Liu, Liangjun Zhang• 2020

Related benchmarks

TaskDatasetResultRank
Depth CompletionNYU-depth-v2 official (test)
RMSE0.106
187
Depth CompletionKITTI depth completion official (test)
RMSE (mm)735.8
154
Depth CompletionKITTI (test)
RMSE735.8
67
Depth CompletionKITTI online leaderboard (test)
MAE0.2172
48
Depth CompletionKITTI depth completion (test)
RMSE735.8
27
Depth CompletionKITTI
iRMSE2.2
24
Depth CompletionNYUv2 500 samples (test)
RMSE (m)0.106
14
Showing 7 of 7 rows

Other info

Follow for update