Geodesy

Quantum mechanics

Algorithm

Benchmark (surveying)

Scale (ratio)

Linguistics

Pixel

Philosophy

Subnetwork

Computer security

Modulation (music)

Operating system

Set (abstract data type)

Computer science

Code (set theory)

Physics

Aesthetics

Source code

Pattern recognition (psychology)

Mathematics

Geography

Inference

Feature (linguistics)

Mathematical analysis

Artificial intelligence

Programming language

Monocular

Generalization

In this paper, we propose Recurrent Multi-Scale Feature Modulation (R-MSFM), a new deep network architecture for self-supervised monocular depth estimation. R-MSFM extracts per-pixel features, builds a multi-scale feature modulation module, and iteratively updates an inverse depth through a parameter-shared decoder at the fixed resolution. This architecture enables our R-MSFM to maintain semantically richer while spatially more precise representations and avoid the error propagation caused by the traditional U-Net-like coarse-to-fine architecture widely used in this domain, resulting in strong generalization and efficient parameter count. Experimental results demonstrate the superiority of our proposed R-MSFM both at model size and inference speed, and show the state-of-the-art results on the KITTI benchmark. Code is available at https://github.com/jsczzzk/R-MSFM

R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating