RigNet: Repetitive Image Guided Network for Depth Completion

TL;DR

RigNet introduces a repetitive, multi-branch image guided network that progressively refines depth maps from sparse data, significantly improving depth completion accuracy on benchmark datasets.

Contribution

The paper proposes a novel repetitive design in both image guidance and depth generation branches, enhancing depth recovery through iterative feature extraction and dynamic convolution modules.

Findings

Achieves superior results on KITTI benchmark.

Performs competitively on NYUv2 dataset.

Demonstrates effective depth map refinement.

Abstract

Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent approaches mainly focus on image guided learning frameworks to predict dense depth. However, blurry guidance in the image and unclear structure in the depth still impede the performance of the image guided frameworks. To tackle these problems, we explore a repetitive design in our image guided network to gradually and sufficiently recover depth values. Specifically, the repetition is embodied in both the image guidance branch and depth generation branch. In the former branch, we design a repetitive hourglass network to extract discriminative image features of complex environments, which can provide powerful contextual instruction for depth prediction. In the latter branch, we introduce a repetitive guidance module based on dynamic convolution, in which an efficient convolution factorization is proposed to simultaneously reduce its complexity and progressively model high-frequency structures. Extensive experiments show that our method achieves superior or competitive results on KITTI benchmark and NYUv2 dataset.