paper-with-me

홈 › Papers

PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction

2024-12-10 · Yujing Xue, Jiaxiang Liu, Jiawei Du, Joey Tianyi Zhou

Recently, polar coordinate-based representations have shown promise for 3D perceptual tasks. Compared to Cartesian methods, polar grids provide a viable alternative, offering better detail preservation in nearby spaces while covering larger areas. However, they face feature distortion due to non-uniform division. To address these issues, we introduce the Polar Voxel Occupancy Predictor (PVP), a novel 3D multi-modal predictor that operates in polar coordinates. PVP features two key design elements to overcome distortion: a Global Represent Propagation (GRP) module that integrates global spatial data into 3D volumes, and a Plane Decomposed Convolution (PD-Conv) that simplifies 3D distortions into 2D convolutions. These innovations enable PVP to outperform existing methods, achieving significant improvements in mIoU and IoU metrics on the OpenOccupancy dataset.

📄 PDF Abstract BibTeX arXiv:2412.07616

Code (0)

등록된 구현이 없습니다.

Tasks

3D Semantic Occupancy Prediction

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Urban Autonomous Agents

2026-03-12 · Mengfei Duan, Hao Shi, Fei Teng, Guoqiang Zhao 외 arxiv

Understanding and reconstructing the 3D world through omnidirectional perception is becoming increasingly important for intelligent transportation and urban autonomous agents operating in shared spaces. However, existing…

Scene Understanding

OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

2023-03-07 · ICCV 2023 1 · XiaoFeng Wang, Zheng Zhu, Wenbo Xu, Yunpeng Zhang 외

Semantic occupancy perception is essential for autonomous driving, as automated vehicles require a fine-grained perception of the 3D urban structures. However, existing relevant benchmarks lack diversity in urban scenes,…

Autonomous DrivingBenchmarkingDiversity

ODG: Occupancy Prediction Using Dual Gaussians

2025-06-11 · Yunxiao Shi, Yinhao Zhu, Shizhong Han, Jisoo Jeong 외

Occupancy prediction infers fine-grained 3D geometry and semantics from camera images of the surrounding environment, making it a critical perception task for autonomous driving. Existing methods either adopt dense grids…

3D geometryAutonomous DrivingPrediction

Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles

2024-02-12 · CVPR 2024 1 · Rui Song, Chenwei Liang, Hu Cao, Zhiran Yan 외

Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bou…

3D Semantic Occupancy PredictionPrediction

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

2023-12-04 · CVPR 2024 1 · Qihang Ma, Xin Tan, Yanyun Qu, Lizhuang Ma 외

The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities. To achieve this, current works try t…

3D geometryAutonomous DrivingDecoderObject Recognition