SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.13802 · 2021

RigNet: Repetitive Image Guided Network for Depth Completion

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2107.13802")
get_code_for_paper("2107.13802")
have("2107.13802")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2107.13802.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2107.13802.svg)](https://syntology.ai/paper/2107.13802)

Connect an agent — have() is free.