SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.07522 · ECCV · 2022

Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation

Jong Ko, Wencan Cheng

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. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Scene flow estimation, which extracts point-wise motion between scenes, is becoming a crucial task in many computer vision tasks. However, all of the existing estimation methods utilize only the unidirectional features, restricting the accuracy and generality. This paper presents a novel scene flow estimation architecture using bidirectional flow embedding layers. The proposed bidirectional layer learns features along both forward and backward directions, enhancing the estimation performance. In addition, hierarchical feature extraction and warping improve the performance and reduce computational overhead. Experimental results show that the proposed architecture achieved a new stateof-the-art record by outperforming other approaches with large margin in both FlyingThings3D and KITTI benchmarks. Codes are available at https://github.com/cwc1260/BiFlow.

For agents

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

get_harvested_code_for_paper("2207.07522")
get_code_for_paper("2207.07522")
have("2207.07522")

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

curl https://syntology.ai/api/ran/2207.07522.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.07522.svg)](https://syntology.ai/paper/2207.07522)

Connect an agent — have() is free.