mlsanityData to 7 Oct 2026

GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation

arXiv 2204.07733 ↗First posted 16 Apr 2022cs.CV cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving for its powerful spatial representation ability. It is challenging to estimate the BEV semantic maps from monocular images due to the spatial gap, since it is implicitly required to realize both the perspective-to-BEV transformation and segmentation. We present a novel two-stage Geometry Prior-based Transformation framework named GitNet, consisting of (i) the geometry-guided pre-alignment and (ii) ray-based transformer. In the first stage, we decouple the BEV segmentation into the perspective image segmentation and geometric prior-based mapping, with explicit supervision by projecting the BEV semantic labels onto the image plane to learn visibility-aware features and learnable geometry to translate into BEV space. Second, the pre-aligned coarse BEV features are further deformed by ray-based transformers to take visibility knowledge into account. GitNet achieves the leading performance on the challenging nuScenes and Argoverse Datasets.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 16 Apr 2022.

Builds on

18 of 24 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  5. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  6. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  7. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  8. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  9. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  10. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  11. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  12. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 173
6 more
  1. 2021Translating Images into Mapscited by 115
  2. 2018Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networkscited by 84
  3. 2020A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye Viewcited by 71
  4. 2020MonoLayout: Amodal scene layout from a single imagecited by 49
  5. 2018Learning to Look around Objects for Top-View Representations of Outdoor Scenescited by 37
  6. 2018Generative Adversarial Frontal View to Bird View Synthesiscited by 25

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 10; 2024: 6; 2025: 4.

24 papers.

Sort:

By area:

  1. 2022Vision-Centric BEV Perception: A Surveycited by 126
  2. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  3. 2023Street-View Image Generation from a Bird's-Eye View Layoutcited by 102
  4. 2023CAPE: Camera View Position Embedding for Multi-View 3D Object Detectioncited by 39
  5. 2023DiffBEV: Conditional Diffusion Model for Bird's Eye View Perceptioncited by 30
  6. 2022LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentationcited by 29
  7. 2023Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Drivingcited by 13
  8. 2024Improving Bird's Eye View Semantic Segmentation by Task Decompositioncited by 13
  9. 2023F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Drivingcited by 12
  10. 2023NeMO: Neural Map Growing System for Spatiotemporal Fusion in Bird's-Eye-View and BDD-Map Benchmarkcited by 11
  11. 2023Semi-Supervised Learning for Visual Bird's Eye View Semantic Segmentationcited by 8
  12. 2023A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentationcited by 7
12 more
  1. 2025Disentangling Instance and Scene Contexts for 3D Semantic Scene Completioncited by 6
  2. 2022Monocular BEV Perception of Road Scenes via Front-to-Top View Projectioncited by 4
  3. 2025U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registrationcited by 4
  4. 2023Multi-camera Bird's Eye View Perception for Autonomous Drivingcited by 2
  5. 2024Focus on BEV: Self-calibrated Cycle View Transformation for Monocular Birds-Eye-View Segmentationcited by 2
  6. 2024VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantizationcited by 2
  7. 2025nuScenes Revisited: Progress and Challenges in Autonomous Drivingcited by 2
  8. 2023DeepSTEP -- Deep Learning-Based Spatio-Temporal End-To-End Perception for Autonomous Vehiclescited by 1
  9. 2024TopView: Vectorising road users in a bird's eye view from uncalibrated street-level imagery with deep learningcited by 1
  10. 2025SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Datasetcited by 1
  11. 2024Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Mapscited by 0
  12. 2024CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box Predictioncited by 0