SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.05367 · ICCV · 2023

Rethinking Range View Representation for LiDAR Segmentation

Ziwei Liu, Yu Qiao, Xinge Zhu, Yikang Li, Lingdong Kong, Runnan Chen, Youquan Liu, Yuexin Ma, Yuenan Hou

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

LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point-or voxel-based methods as they often yield better performance than the traditional range view representation. In this work, we unveil several key factors in building powerful range view models. We observe that the "many-to-one" mapping, semantic incoherence, and shape deformation are possible impediments against effective learning from range view projections. We present RangeFormer -a full-cycle framework comprising novel designs across network architecture, data augmentation, and post-processing -that better handles the learning and processing of LiDAR point clouds from the range view. We further introduce a Scalable Training from Range view (STR) strategy that trains on arbitrary lowresolution 2D range images, while still maintaining satisfactory 3D segmentation accuracy. We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i.e., SemanticKITTI, nuScenes, and ScribbleKITTI.

For agents

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

get_harvested_code_for_paper("2303.05367")
get_code_for_paper("2303.05367")
have("2303.05367")

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

curl https://syntology.ai/api/ran/2303.05367.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.05367.svg)](https://syntology.ai/paper/2303.05367)

Connect an agent — have() is free.