mlsanityData to 14 Oct 2026

Forecasting Future Instance Segmentation with Learned Optical Flow and Warping

arXiv 2211.08049 ↗First posted 15 Nov 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others. This can be done using different sensors and modalities. In this paper we investigate the usage of optical flow for predicting future semantic segmentations. To do so we propose a model that forecasts flow fields autoregressively. Such predictions are then used to guide the inference of a learned warping function that moves instance segmentations on to future frames. Results on the Cityscapes dataset demonstrate the effectiveness of optical-flow methods.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 15 Nov 2022.

Builds on

24 of 34 references.

References · 24

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Mask R-CNNcited by 7,277
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  7. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  8. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  9. 2019Panoptic Feature Pyramid Networkscited by 645
  10. 2015Deep multi-scale video prediction beyond mean square errorcited by 300
  11. 2020Learning to Detect Objects with a 1 Megapixel Event Cameracited by 186
  12. 2017Decomposing Motion and Content for Natural Video Sequence Predictioncited by 169
12 more
  1. 2020A Review on Deep Learning Techniques for Video Predictioncited by 114
  2. 2016Video Pixel Networkscited by 108
  3. 2017Predicting Deeper into the Future of Semantic Segmentationcited by 51
  4. 2018Predicting Future Instance Segmentation by Forecasting Convolutional Featurescited by 37
  5. 2018BirdNet: a 3D Object Detection Framework from LiDAR informationcited by 33
  6. 2017Illuminating Pedestrians via Simultaneous Detection & Segmentationcited by 26
  7. 2018Recurrent Flow-Guided Semantic Forecastingcited by 19
  8. 2019Segmenting the Futurecited by 19
  9. 2019Single Level Feature-to-Feature Forecasting with Deformable Convolutionscited by 10
  10. 2021Panoptic Segmentation Forecastingcited by 7
  11. 2016Segmentation Free Object Discovery in Videocited by 3
  12. 2018Semantic Road Layout Understanding by Generative Adversarial Inpaintingcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2024MemFlow: Optical Flow Estimation and Prediction with Memorycited by 55
  2. 2025Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformerscited by 8
  3. 2023FLODCAST: Flow and Depth Forecasting via Multimodal Recurrent Architecturescited by 2
  4. 2022Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Timecited by 0