Cover Image

InstanceBEV: Unifying Instance and BEV Representation for 3D Panoptic Segmentation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Feng, Wang, Zhaoyue, Zhang, Enyuan, Billah, Mohammad Masum, Cui, Yunduan, Xu, Kun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy
by: Zhang, Zaibin, et al.
Published: (2023)

MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation
by: Zhao, Xiao, et al.
Published: (2024)

LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance Representation
by: Ma, Weijie, et al.
Published: (2024)

Refine-and-Contrast: Adaptive Instance-Aware BEV Representations for Multi-UAV Collaborative Object Detection
by: Li, Zhongyao, et al.
Published: (2025)

GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection
by: Zhang, Jinqing, et al.
Published: (2024)

BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving
by: Antunes-García, Miguel, et al.
Published: (2026)

GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection
by: Song, Ziying, et al.
Published: (2024)

SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation
by: Ye, Junyan, et al.
Published: (2024)

DenseBEV: Transforming BEV Grid Cells into 3D Objects
by: Dähling, Marius, et al.
Published: (2025)

DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences
by: Li, Peidong, et al.
Published: (2024)

PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation
by: Qiu, Shoumeng, et al.
Published: (2024)

Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
by: Wu, Yizheng, et al.
Published: (2024)

ChatBEV: A Visual Language Model that Understands BEV Maps
by: Xu, Qingyao, et al.
Published: (2025)

Cues3D: Unleashing the Power of Sole NeRF for Consistent and Unique Instances in Open-Vocabulary 3D Panoptic Segmentation
by: Xue, Feng, et al.
Published: (2025)

PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction
by: Yu, Xuan, et al.
Published: (2024)

ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object Detection
by: Chen, Jiwei, et al.
Published: (2024)

RESAR-BEV: An Explainable Progressive Residual Autoregressive Approach for Camera-Radar Fusion in BEV Segmentation
by: Zeng, Zhiwen, et al.
Published: (2025)

TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation
by: Xu, Shaoqing, et al.
Published: (2024)

BEV$^2$PR: BEV-Enhanced Visual Place Recognition with Structural Cues
by: Ge, Fudong, et al.
Published: (2024)

BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving
by: Tang, Tao, et al.
Published: (2024)

An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving
by: Feng, Yi, et al.
Published: (2026)

Privacy-Concealing Cooperative Perception for BEV Scene Segmentation
by: Wang, Song, et al.
Published: (2026)

Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation
by: Mansour, Elham Amin, et al.
Published: (2024)

Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
by: Großkopf, Erik, et al.
Published: (2026)

BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving
by: Brandstaetter, Felix, et al.
Published: (2025)

BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation
by: Cong, Hiep Truong, et al.
Published: (2025)

InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
by: Li, Haijie, et al.
Published: (2024)

UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities
by: Wang, Shiming, et al.
Published: (2023)

IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
by: Gross, Markus, et al.
Published: (2025)

FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras
by: Li, Hang, et al.
Published: (2025)

Split&Splat: Zero-Shot Panoptic Segmentation via Explicit Instance Modeling and 3D Gaussian Splatting
by: Monchieri, Leonardo, et al.
Published: (2026)

HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection
by: Wu, Di, et al.
Published: (2024)

SABER: Spatially Consistent 3D Universal Adversarial Objects for BEV Detectors
by: Li, Aixuan, et al.
Published: (2025)

Panoptic-FlashOcc: An Efficient Baseline to Marry Semantic Occupancy with Panoptic via Instance Center
by: Yu, Zichen, et al.
Published: (2024)

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting
by: Lu, Yiren, et al.
Published: (2026)

FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection
by: Jiang, Zheng, et al.
Published: (2024)

TempBEV: Improving Learned BEV Encoders with Combined Image and BEV Space Temporal Aggregation
by: Monninger, Thomas, et al.
Published: (2024)

MambaBEV: An EV-based 3D detection model with Mamba2
by: You, Zihan, et al.
Published: (2024)

Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
by: Li, Bohan, et al.
Published: (2023)

Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps
by: Monaci, Gianluca, et al.
Published: (2024)