paper-with-me

홈 › Papers

Up-to-Down Network: Fusing Multi-Scale Context for 3D Semantic Scene Completion

2021-09-27 · IEEE International Workshop on Intelligent Robots and Systems (IROS) 2021 9 · Hao Zou, Xuemeng Yang, Tianxin Huang, Chujuan Zhang, Yong liu, Wanlong Li, Feng Wen, Hongbo Zhang

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

3D Semantic Scene CompletionAutonomous DrivingDecoder

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Pyramid Pooling Module A Pyramid Pooling Module is a module for semantic segmentation which acts as an effective global contextual prior. The motivation is that the problem of using a convolutional…
Spatial Pyramid Pooling Spatial Pyramid Pooling (SPP) is a pooling layer that removes the fixed-size constraint of the network, i.e. a CNN does not require a fixed-size input image. Specifically, we…

Similar Papers 제목 키워드 기반

ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation

2019-06-01 · CVPR 2019 6 · Di Lin, Dingguo Shen, Siting Shen, Yuanfeng Ji 외

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 Segmentation

Technical Report on Subspace Pyramid Fusion Network for Semantic Segmentation

2022-04-04 · Mohammed A. M. Elhassan, Chenhui Yang, Chenxi Huang, Tewodros Legesse Munea

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 Segmentation

Feature Selective Transformer for Semantic Image Segmentation

2022-03-26 · Fangjian Lin, Tianyi Wu, Sitong Wu, Shengwei Tian 외

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 Segmentation

Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation

2021-06-03 · Yechao Bai, Ziyuan Huang, Lyuyu Shen, Hongliang Guo 외

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 Segmentation

End-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching

2019-06-25 · Li Zhang, Quanhong Wang, Haihua Lu, Yong Zhao

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