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

2025/07/09 by Marcel Voßhans, Omar Ait-Aider, Vosshans, Marcel +5
Computer Science · Engineering · #Advanced Neural Network Applications #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2507.06687

openalex publication_date 2025/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Depth Anything V2
• StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection
• SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
• Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors
• Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
• Learning Occupancy for Monocular 3D Object Detection
• Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloud
• LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
• A ConvNet for the 2020s
• A ConvNet for the 2020s
• MonoScene: Monocular 3D Semantic Scene Completion
• Translating Images into Maps
• Probabilistic and Geometric Depth: Detecting Objects in Perspective
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• Searching for MobileNetV3
• CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
• Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
• MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• Attention Is All You Need
• Unsupervised Monocular Depth Estimation with Left-Right Consistency
• Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Related

• StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection
• LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception
• AOP-Net: All-in-One Perception Network for Joint LiDAR-based 3D Object Detection and Panoptic Segmentation
• LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network
• MonoDistill: Learning Spatial Features for Monocular 3D Object Detection