Achieving RGB-D level Segmentation Performance from a Single ToF Camera
Not on the map. Why?
Abstract (arXiv)
Depth is a very important modality in computer vision, typically used as complementary information to RGB, provided by RGB-D cameras. In this work, we show that it is possible to obtain the same level of accuracy as RGB-D cameras on a semantic segmentation task using infrared (IR) and depth images from a single Time-of-Flight (ToF) camera. In order to fuse the IR and depth modalities of the ToF camera, we introduce a method utilizing depth-specific convolutions in a multi-task learning framework. In our evaluation on an in-car segmentation dataset, we demonstrate the competitiveness of our method against the more costly RGB-D approaches.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 30 Jun 2023.
Builds on
11 of 25 references.
References · 11
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2016Cross-stitch Networks for Multi-task Learningcited by 466
- 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
- 2021ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentationcited by 75
- 2018Depth-aware CNN for RGB-D Segmentationcited by 73
- 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
- 2021TICaM: A Time-of-flight In-car Cabin Monitoring Datasetcited by 10
- 2021TIMo -- A Dataset for Indoor Building Monitoring with a Time-of-Flight Cameracited by 9
- 20193D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentationcited by 6
- 2022Unsupervised Anomaly Detection from Time-of-Flight Depth Imagescited by 6
- 2021Review on Indoor RGB-D Semantic Segmentation with Deep Convolutional Neural Networkscited by 3
Built on by
Not cited yet.