StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Object SegmentationScene SegmentationSimilar Papers 제목 키워드 기반
StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection
In this work, we present a novel approach for general object segmentation from a monocular image, eliminating the need for manually labeled training data and enabling rapid, straightforward training and adaptation with m…
Semantic SegmentationLightweight Monocular Depth Estimation
Monocular depth estimation can play an important role in addressing the issue of deriving scene geometry from 2D images. It has been used in a variety of industries, including robots, self-driving cars, scene comprehensi…
Depth EstimationImage SegmentationMonocular Depth EstimationSelf-Driving Cars+1MultiDepth: Multi-Sample Priors for Refining Monocular Metric Depth Estimations in Indoor Scenes
Monocular metric depth estimation (MMDE) is a crucial task to solve for indoor scene reconstruction on edge devices. Despite this importance, existing models are sensitive to factors such as boundary frequency of objects…
DecoderDepth EstimationIndoor Scene ReconstructionMonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language. However, current 3D Gauss…
Scene UnderstandingQuestion AnsweringLEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction
Scene graphs are becoming a standard representation for robot navigation, providing hierarchical geometric and semantic scene understanding. However, most scene graph mapping methods rely on depth cameras or LiDAR sensor…
Object SegmentationScene UnderstandingRobot Navigation