(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network

Cheng, Ran; Razani, Ryan; Taghavi, Ehsan; Li, Enxu; Liu, Bingbing

doi:10.48550/arxiv.2102.04530

Cited by 9 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-view fusion-based methods combine voxel-based, projection-based and/or point-wise operations for LiDAR point clouds segmentation. To extract more semantic information, some recent methods [35], [36], [37], [38], [39], [40], [41], [7], [8] blend two or more different views together. For instance, [38], [39] combine point-wise information from BEV and range-image in early-stage, and then feed it to the subsequent network.…”

Section: B Lidar Point Cloud Semantic Segmentationmentioning

confidence: 99%

“…2 -S3Net [7] use point-voxel fusion scheme to achieve better segmentation results. RPVNet [8] proposes a deep fusion network to fuse range-point-voxel three views by a gated fusion mechanism.…”

Section: B Lidar Point Cloud Semantic Segmentationmentioning

confidence: 99%

“…As mentioned above, although LiDAR points can provide accurate distance measurements and capture the structures of objects, they are usually sparse, unordered, and unevenly distributed. Recently, some methods [5], [6], [7], [8] based only on LiDAR have significantly improved the performance of 3D semantic segmentation, but the performance of these methods are still limited because of lacking dense and rich information on the objects such as their colors, and textures, as depicted in the right of Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation

Zhao,

Zhou,

Zhu

et al. 2021

Preprint

View full text Add to dashboard Cite

Camera and 3D LiDAR sensors have become indispensable devices in modern autonomous driving vehicles, where the camera provides the fine-grained texture, color information in 2D space and LiDAR captures more precise and farther-away distance measurements of the surrounding environments. The complementary information from these two sensors makes the two-modality fusion be a desired option. However, two major issues of the fusion between camera and LiDAR hinder its performance, i.e., how to effectively fuse these two modalities and how to precisely align them (suffering from the weak spatiotemporal synchronization problem). In this paper, we propose a coarse-to-fine LiDAR and camera fusion-based network (termed as LIF-Seg) for LiDAR segmentation. For the first issue, unlike these previous works fusing the point cloud and image information in a one-to-one manner, the proposed method fully utilizes the contextual information of images and introduces a simple but effective early-fusion strategy. Second, due to the weak spatiotemporal synchronization problem, an offset rectification approach is designed to align these two-modality features. The cooperation of these two components leads to the success of the effective camera-LiDAR fusion. Experimental results on the nuScenes dataset show the superiority of the proposed LIF-Seg over existing methods with a large margin. Ablation studies and analyses demonstrate that our proposed LIF-Seg can effectively tackle the weak spatiotemporal synchronization problem.

show abstract

Section: B Lidar Point Cloud Semantic Segmentationmentioning

confidence: 99%

Section: B Lidar Point Cloud Semantic Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation

Zhao,

Zhou,

Zhu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We only compare with methods that report both accuracy and runtime. The methods in comparison are: CenterPoint [34](CP), HotSpotNet [6](H), CVCNet [5](CVC), PointPainting [28](PNT), PointPillars [15](PP),SAPNET [33](S), AF2S3Net [8](A), Cylinder3D [36](C3D), PolarNet [35](PLN),SPVNAS [27](SPV), SalsaNext [9]+CBGS [40](S+C), Po-larNet+CBGS(P+C) and PaP [39](PaP). We color our methods in green and other methods in red.…”

Section: How Streaming Models Enlarge Contextmentioning

confidence: 99%

PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars

Chen¹,

Vora²,

Beijbom³

2021

Preprint

View full text Add to dashboard Cite

Recent works recognized lidars as an inherently streaming data source and showed that the end-to-end latency of lidar perception models can be reduced significantly by operating on wedge-shaped point cloud sectors rather then the full point cloud. However, due to use of cartesian coordinate systems these methods represent the sectors as rectangular regions, wasting memory and compute. In this work we propose using a polar coordinate system and make two key improvements on this design. First, we increase the spatial context by using multi-scale padding from neighboring sectors: preceding sector from the current scan and/or the following sector from the past scan. Second, we improve the core polar convolutional architecture by introducing feature undistortion and range stratified convolutions. Experimental results on the nuScenes dataset show significant improvements over other streaming based methods. We also achieve comparable results to existing non-streaming methods but with lower latencies.

show abstract

“…It lacks the ability to process more general unordered point clouds, but it shows practical advantages such as better performance in terms of both the speed and accuracy [6], [7]. To chase a better performance, recent researchers further design models by combining multiview projections or voxelization with point-wise features [8], [9], [10].…”

Section: Introductionmentioning

confidence: 99%