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

arXiv: https://arxiv.org/abs/2507.06687 · HTML: https://mlsanity.com/paper/2507.06687/

## 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 (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [Translating Images into Maps](https://mlsanity.com/paper/2110.00966/) (2021)
- [Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks](https://mlsanity.com/paper/1605.02305/) (2016)
- [MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization](https://mlsanity.com/paper/1811.10247/) (2018)
- [CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth](https://mlsanity.com/paper/1904.02028/) (2019)
- [Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloud](https://mlsanity.com/paper/2207.11919/) (2022)
- [Learning Occupancy for Monocular 3D Object Detection](https://mlsanity.com/paper/2305.15694/) (2023)
- [LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection](https://mlsanity.com/paper/2206.07705/) (2022)
- [Learning Depth from Single Images with Deep Neural Network Embedding Focal Length](https://mlsanity.com/paper/1803.10039/) (2018)
- [Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors](https://mlsanity.com/paper/2403.06093/) (2024)
- [SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects](https://mlsanity.com/paper/2403.20318/) (2024)
- [You Only Look Bottom-Up for Monocular 3D Object Detection](https://mlsanity.com/paper/2401.15319/) (2024)
- [Mono-Stixels: Monocular depth reconstruction of dynamic street scenes](https://mlsanity.com/paper/1908.02635/) (2019)
- [StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection](https://mlsanity.com/paper/2407.08277/) (2024)

## 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.