Generative Map Priors for Collaborative BEV Semantic Segmentation
Collaborative perception aims to address the constraint of single-agent perception by exchanging information among multiple agents. Previous works primarily focus on collaborative object detection, exploring compressed transmission and fusion prediction tailored to sparse object features. However, these strategies are not well-suited for dense features in collaborative BEV semantic segmentation. Therefore, we propose CoGMP, a novel Collaborative framework that leverages Generative Map Priors to achieve efficient compression and robust fusion. CoGMP introduces two key innovations: Element Format Feature Compression (EFFC) and Structure Guided Feature Fusion (SGFF). Specifically, EFFC leverages map element priors from codebook to encode BEV features as discrete element indices for transmitted information compression. Meanwhile, SGFF utilizes a diffusion model with structural priors to coherently integrate multi-agent features, thereby achieving consistent fusion predictions. Evaluations on the OPV2V dataset show that CoGMP achieves a 6.89/7.64 Road/Lane IoU improvement and a 32-fold reduction in communication volume.
Code (0)
등록된 구현이 없습니다.
Tasks
Feature Compressionobject-detectionObject DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generative ScatterNet Hybrid Deep Learning (G-SHDL) Network with Structural Priors for Semantic Image Segmentation
This paper proposes a generative ScatterNet hybrid deep learning (G-SHDL) network for semantic image segmentation. The proposed generative architecture is able to train rapidly from relatively small labeled datasets usin…
General ClassificationImage SegmentationSemantic SegmentationMatterDoor: Sampling Zero-shot Spatio-semantic Priors using Generative Models
Autonomous robots often view rooms only partially, through a doorway, where the walls and scene structure hide the geometry and task-relevant semantics needed for safe navigation and goal-directed action. We ask whether …
Monocular Depth EstimationSemantic SegmentationFace Completion with Semantic Knowledge and Collaborative Adversarial Learning
Unlike a conventional background inpainting approach that infers a missing area from image patches similar to the background, face completion requires semantic knowledge about the target object for realistic outputs. Cur…
Facial InpaintingImage InpaintingSemantic SegmentationLatents2Segments: Disentangling the Latent Space of Generative Models for Semantic Segmentation of Face Images
With the advent of an increasing number of Augmented and Virtual Reality applications that aim to perform meaningful and controlled style edits on images of human faces, the impetus for the task of parsing face images to…
DisentanglementSegmentationSemantic SegmentationHumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
Recent advances in generative models have achieved high-fidelity in 3D human reconstruction, yet their utility for specific tasks (e.g., human 3D segmentation) remains constrained. We propose HumanCrafter, a unified fram…
3D Human Reconstruction