论文标题
朝向细粒大型对象分割第一第一个求解解决方案到3D AI挑战2020-实例分割轨道
Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track
论文作者
论文摘要
该技术报告介绍了我们团队“ FineGrainedSeg”的解决方案，例如2020年3D AI挑战中的细分轨道。为了在3D-Future中处理极大的对象，我们采用Pointrend作为基本框架，该框架与HTC和SOLOV2相比，它输出了更细粒度的面具。我们的最终提交是由5种Pointrend模型组成的合奏，该模型在验证和测试排行榜上都获得了第一名。该代码可在https://github.com/zehuichen123/3dfuture_ins_seg上找到。
This technical report introduces our solutions of Team 'FineGrainedSeg' for Instance Segmentation track in 3D AI Challenge 2020. In order to handle extremely large objects in 3D-FUTURE, we adopt PointRend as our basic framework, which outputs more fine-grained masks compared to HTC and SOLOv2. Our final submission is an ensemble of 5 PointRend models, which achieves the 1st place on both validation and test leaderboards. The code is available at https://github.com/zehuichen123/3DFuture_ins_seg.
