mlsanityData to 7 Oct 2026

OC-SOP: Enhancing Vision-Based 3D Semantic Occupancy Prediction by Object-Centric Awareness

arXiv 2506.18798 ↗First posted 23 Jun 2025cs.CV cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous driving perception faces significant challenges due to occlusions and incomplete scene data in the environment. To overcome these issues, the task of semantic occupancy prediction (SOP) is proposed, which aims to jointly infer both the geometry and semantic labels of a scene from images. However, conventional camera-based methods typically treat all categories equally and primarily rely on local features, leading to suboptimal predictions, especially for dynamic foreground objects. To address this, we propose Object-Centric SOP (OC-SOP), a framework that integrates high-level object-centric cues extracted via a detection branch into the semantic occupancy prediction pipeline. This object-centric integration significantly enhances the prediction accuracy for foreground objects and achieves state-of-the-art performance among all categories on SemanticKITTI.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

30 of 43 references.

References · 30

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  6. 2020Object-Centric Learning with Slot Attentioncited by 865
  7. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  8. 2020Convolutional Occupancy Networkscited by 760
  9. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  10. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  11. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
18 more
  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  2. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  3. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  4. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  5. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  6. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 187
  7. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 126
  8. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  9. 20213D Semantic Scene Completion: a Surveycited by 74
  10. 2021Panoptic 3D Scene Reconstruction From a Single RGB Imagecited by 70
  11. 2023Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactionscited by 19
  12. 2024Image Fusion for Cross-Domain Sequential Recommendationcited by 17
  13. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Modelscited by 16
  14. 2024Prompt Categories Cluster for Weakly Supervised Semantic Segmentationcited by 16
  15. 2024SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Netcited by 12
  16. 2025LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendationcited by 11
  17. 2024Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Reviewcited by 9
  18. 2025ICG-MVSNet: Learning Intra-view and Cross-view Relationships for Guidance in Multi-View Stereocited by 2

Built on by

Not cited yet.