mlsanityData to 13 Oct 2026

SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection

arXiv 2608.16338 ↗First posted 17 Aug 2026cs.CV cs.AIcited by 0

On the map: State-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing

Abstract (arXiv)

Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues. In streaming recurrent models, corrupted observations may enter the hidden state and produce errors that persist into later frames. Existing occlusion-aware refinements usually provide obstacle masks as auxiliary inputs, so the state-update path is only indirectly protected. We propose SIGMA-Lane, which treats this failure mode as state contamination in State Space Model (SSM)-based temporal modeling. SIGMA-Lane places occlusion-aware gates on the SSM write and residual-fusion paths, controlling how current observations enter temporal memory and are fused back after temporal propagation. After coordinate-consistent affine alignment, the model combines two complementary paths: SSM-consistent dual-gating for temporal filtering and Structural Spatial Retrieval (SSR) for recovering missing lane structure from aligned historical priors. Experiments on VIL-100 and OpenLane-V show improved temporal stability under heavy occlusion, with competitive F1 and mIoU scores.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 32 of its 41 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

32 of 41 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,658
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,930
  5. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,440
  6. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,307
  7. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,055
  8. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  9. 2017Spatial As Deep: Spatial CNN for Traffic Scene Understandingcited by 187
  10. 2019Learning Lightweight Lane Detection CNNs by Self Attention Distillationcited by 162
  11. 2020Keep your Eyes on the Lane: Real-time Attention-guided Lane Detectioncited by 138
  12. 2018Towards End-to-End Lane Detection: an Instance Segmentation Approachcited by 129
20 more
  1. 2020Ultra Fast Structure-aware Deep Lane Detectioncited by 121
  2. 2020End-to-end Lane Shape Prediction with Transformerscited by 111
  3. 2020PolyLaneNet: Lane Estimation via Deep Polynomial Regressioncited by 95
  4. 2021CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolutioncited by 95
  5. 2022Rethinking Efficient Lane Detection via Curve Modelingcited by 88
  6. 2022CLRNet: Cross Layer Refinement Network for Lane Detectioncited by 82
  7. 2020CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blendingcited by 80
  8. 2020RESA: Recurrent Feature-Shift Aggregator for Lane Detectioncited by 77
  9. 2022A Keypoint-based Global Association Network for Lane Detectioncited by 68
  10. 2020Inter-Region Affinity Distillation for Road Marking Segmentationcited by 58
  11. 2019Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networkscited by 41
  12. 2022Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanescited by 32
  13. 2021VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detectioncited by 21
  14. 2022RCLane: Relay Chain Prediction for Lane Detectioncited by 20
  15. 2023ADNet: Lane Shape Prediction via Anchor Decompositioncited by 14
  16. 2023Recursive Video Lane Detectioncited by 9
  17. 2026DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Drivingcited by 9
  18. 2024Lane2Seq: Towards Unified Lane Detection via Sequence Generationcited by 5
  19. 2024OMR: Occlusion-Aware Memory-Based Refinement for Video Lane Detectioncited by 4
  20. 2024LaneTCA: Enhancing Video Lane Detection with Temporal Context Aggregationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models
  2. 2026OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning
  3. 2025DiffusionLane: Diffusion Model for Lane Detection
  4. 2025TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Driving
  5. 2023LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
  6. 2024Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection
  7. 2021On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving
  8. 2025OpenLKA: An Open Dataset of Lane Keeping Assist from Recent Car Models under Real-world Driving Conditions