mlsanityData to 14 Oct 2026

StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception

arXiv 2507.06687 ↗First posted 9 Jul 2025cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents StixelNExT++, a novel approach to scene representation for monocular perception systems. Building on the established Stixel representation, our method infers 3D Stixels and enhances object segmentation by clustering smaller 3D Stixel units. The approach achieves high compression of scene information while remaining adaptable to point cloud and bird's-eye-view representations. Our lightweight neural network, trained on automatically generated LiDAR-based ground truth, achieves real-time performance with computation times as low as 10 ms per frame. Experimental results on the Waymo dataset demonstrate competitive performance within a 30-meter range, highlighting the potential of StixelNExT++ for collective perception in autonomous systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 9 Jul 2025.

Builds on

26 of 40 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2022A ConvNet for the 2020scited by 3,579
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  5. 2019Searching for MobileNetV3cited by 1,994
  6. 2024Depth Anything V2cited by 1,422
  7. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  8. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  9. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  11. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  12. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
14 more
  1. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  2. 2021Translating Images into Mapscited by 115
  3. 2016Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networkscited by 91
  4. 2018MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localizationcited by 84
  5. 2019CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthcited by 75
  6. 2022Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloudcited by 47
  7. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 36
  8. 2022LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detectioncited by 27
  9. 2018Learning Depth from Single Images with Deep Neural Network Embedding Focal Lengthcited by 25
  10. 2024Enhancing 3D Object Detection with 2D Detection-Guided Query Anchorscited by 12
  11. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
  12. 2024You Only Look Bottom-Up for Monocular 3D Object Detectioncited by 3
  13. 2019Mono-Stixels: Monocular depth reconstruction of dynamic street scenescited by 2
  14. 2024StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detectioncited by 1

Built on by

Not cited yet.