Up-to-Down Network: Fusing Multi-Scale Context for 3D Semantic Scene Completion
An efficient 3D scene perception algorithm is a vital component for autonomous driving and robotics systems. In this paper, we focus on semantic scene completion, which is a task of jointly estimating the volumetric occupancy and semantic labels of objects. Since the real-world data is sparse and occluded, this is an extremely challenging task. We propose a novel framework, named Up-to-Down network (UDNet), to achieve the large-scale semantic scene completion with an encoder-decoder architecture for voxel grids. The novel up-to-down block can effectively aggregate multi-scale context information to improve labeling coherence, and the atrous spatial pyramid pooling module is leveraged to expand the receptive field while preserving detailed geometric information. Besides, the proposed multi-scale fusion mechanism efficiently aggregates global background information and improves the semantic completion accuracy. Moreover, to further satisfy the needs of different tasks, our UDNet can accomplish the multi-resolution semantic completion, achieving faster but coarser completion. Detailed experiments in the semantic scene completion benchmark of SemanticKITTI illustrate that our proposed framework surpasses the state-of-the-art methods with remarkable margins and a real-time inference speed by using only voxel grids as input.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Semantic Scene CompletionAutonomous DrivingDecoderMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation
Multi-scale context information has proven to be essential for object segmentation tasks. Recent works construct the multi-scale context by aggregating convolutional feature maps extracted by different levels of a deep n…
Instance SegmentationSegmentationSemantic SegmentationTechnical Report on Subspace Pyramid Fusion Network for Semantic Segmentation
The following is a technical report to test the validity of the proposed Subspace Pyramid Fusion Module (SPFM) to capture multi-scale feature representations, which is more useful for semantic segmentation. In this inves…
SegmentationSemantic SegmentationFeature Selective Transformer for Semantic Image Segmentation
Recently, it has attracted more and more attentions to fuse multi-scale features for semantic image segmentation. Various works were proposed to employ progressive local or global fusion, but the feature fusions are not …
feature selectionImage SegmentationSegmentationSemantic SegmentationMulti-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation
Exploiting multi-scale features has shown great potential in tackling semantic segmentation problems. The aggregation is commonly done with sum or concatenation (concat) followed by convolutional (conv) layers. However, …
Panoptic SegmentationRelationSegmentationSemantic SegmentationEnd-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching
Deep neural networks have shown excellent performance in stereo matching task. Recently CNN-based methods have shown that stereo matching can be formulated as a supervised learning task. However, less attention is paid o…
Disparity EstimationStereo MatchingStereo Matching Hand