FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding

8 Sep 2021  ·  Yiming Zhao, Lin Bai, Xinming Huang ·

Projecting the point cloud on the 2D spherical range image transforms the LiDAR semantic segmentation to a 2D segmentation task on the range image. However, the LiDAR range image is still naturally different from the regular 2D RGB image; for example, each position on the range image encodes the unique geometry information. In this paper, we propose a new projection-based LiDAR semantic segmentation pipeline that consists of a novel network structure and an efficient post-processing step. In our network structure, we design a FID (fully interpolation decoding) module that directly upsamples the multi-resolution feature maps using bilinear interpolation. Inspired by the 3D distance interpolation used in PointNet++, we argue this FID module is a 2D version distance interpolation on $(\theta, \phi)$ space. As a parameter-free decoding module, the FID largely reduces the model complexity by maintaining good performance. Besides the network structure, we empirically find that our model predictions have clear boundaries between different semantic classes. This makes us rethink whether the widely used K-nearest-neighbor post-processing is still necessary for our pipeline. Then, we realize the many-to-one mapping causes the blurring effect that some points are mapped into the same pixel and share the same label. Therefore, we propose to process those occluded points by assigning the nearest predicted label to them. This NLA (nearest label assignment) post-processing step shows a better performance than KNN with faster inference speed in the ablation study. On the SemanticKITTI dataset, our pipeline achieves the best performance among all projection-based methods with $64 \times 2048$ resolution and all point-wise solutions. With a ResNet-34 as the backbone, both the training and testing of our model can be finished on a single RTX 2080 Ti with 11G memory. The code is released.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Semi-Supervised Semantic Segmentation nuScenes Sup.-only (Range View) mIoU (1% Labels) 38.3 # 9
mIoU (10% Labels) 57.5 # 9
mIoU (20% Labels) 62.7 # 9
mIoU (50% Labels) 67.6 # 9
Robust 3D Semantic Segmentation nuScenes-C FIDNet mean Corruption Error (mCE) 122.42% # 12
Semi-Supervised Semantic Segmentation ScribbleKITTI Sup.-only (Range View) mIoU (1% Labels) 33.1 # 9
mIoU (10% Labels) 47.7 # 9
mIoU (20% Labels) 49.9 # 9
mIoU (50% Labels) 52.5 # 9
Robust 3D Semantic Segmentation SemanticKITTI-C FIDNet (64x2048) mean Corruption Error (mCE) 113.81% # 16

Methods


No methods listed for this paper. Add relevant methods here