Copertina

Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nishimura, Toshihiko, Abe, Hirofumi, Murasaki, Kazuhiko, Yoshida, Taiga, Tanida, Ryuichi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Memory-Efficient Point Cloud Registration via Overlapping Region Sampling
di: Shimada, Tomoyasu, et al.
Pubblicazione: (2024)

Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmission
di: Murasaki, Kazuhiko, et al.
Pubblicazione: (2026)

Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept
di: Sato, Shogo, et al.
Pubblicazione: (2025)

Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training
di: Sato, Shogo, et al.
Pubblicazione: (2024)

Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking
di: Inoue, Riku, et al.
Pubblicazione: (2026)

IPCD: Intrinsic Point-Cloud Decomposition
di: Sato, Shogo, et al.
Pubblicazione: (2025)

ComptonUNet: A Deep Learning Model for GRB Localization with Compton Cameras under Noisy and Low-Statistic Conditions
di: Sato, Shogo, et al.
Pubblicazione: (2026)

LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds
di: Tsuji, Masahiko, et al.
Pubblicazione: (2025)

LabelGS: Label-Aware 3D Gaussian Splatting for 3D Scene Segmentation
di: Zhang, Yupeng, et al.
Pubblicazione: (2025)

Controllable 3D Outdoor Scene Generation via Scene Graphs
di: Liu, Yuheng, et al.
Pubblicazione: (2025)

Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding
di: Hsu, Chih-Chung, et al.
Pubblicazione: (2025)

SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding
di: Zheng, Hongpei, et al.
Pubblicazione: (2025)

ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
di: Ji, Guangda, et al.
Pubblicazione: (2024)

6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstruction
di: Gieruc, Théo, et al.
Pubblicazione: (2024)

SceneTeract: Agentic Functional Affordances and VLM Grounding in 3D Scenes
di: Maillard, Léopold, et al.
Pubblicazione: (2026)

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
di: Jin, Bu, et al.
Pubblicazione: (2024)

R3GW: Relightable 3D Gaussians for Outdoor Scenes in the Wild
di: Corona, Margherita Lea, et al.
Pubblicazione: (2026)

Spectral Probing of Feature Upsamplers in 2D-to-3D Scene Reconstruction
di: Xiao, Ling, et al.
Pubblicazione: (2026)

Leveraging VLM-Based Pipelines to Annotate 3D Objects
di: Kabra, Rishabh, et al.
Pubblicazione: (2023)

Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding
di: Rao, Yuchen, et al.
Pubblicazione: (2025)

Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding
di: Yin, Xingyilang, et al.
Pubblicazione: (2025)

FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
di: Jiang, Chenhan, et al.
Pubblicazione: (2026)

FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding
di: Zhan, Chenlu, et al.
Pubblicazione: (2025)

Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models
di: Xu, Yifan, et al.
Pubblicazione: (2025)

EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene
di: Huo, Yixiong, et al.
Pubblicazione: (2024)

UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes
di: Rozenberszki, David, et al.
Pubblicazione: (2023)

STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
di: Yang, Jiawei, et al.
Pubblicazione: (2024)

PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding
di: Jung, Seongmin, et al.
Pubblicazione: (2025)

Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds
di: Gong, Haoran, et al.
Pubblicazione: (2024)

Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models
di: Berman, Nimrod, et al.
Pubblicazione: (2025)

In-Place Panoptic Radiance Field Segmentation with Perceptual Prior for 3D Scene Understanding
di: Li, Shenghao
Pubblicazione: (2024)

Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
di: Cheng, Chong, et al.
Pubblicazione: (2025)

SAI3D: Segment Any Instance in 3D Scenes
di: Yin, Yingda, et al.
Pubblicazione: (2023)

Large-scale Photorealistic Outdoor 3D Scene Reconstruction from UAV Imagery Using Gaussian Splatting Techniques
di: Maikos, Christos, et al.
Pubblicazione: (2026)

StyleCity: Large-Scale 3D Urban Scenes Stylization
di: Chen, Yingshu, et al.
Pubblicazione: (2024)

Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding
di: Huang, Wencan, et al.
Pubblicazione: (2025)

ROOT: VLM based System for Indoor Scene Understanding and Beyond
di: Wang, Yonghui, et al.
Pubblicazione: (2024)

GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections
di: Bai, Haiyang, et al.
Pubblicazione: (2025)

MultiBARF: Integrating Imagery of Different Wavelength Regions by Using Neural Radiance Fields
di: Kurata, Kana, et al.
Pubblicazione: (2025)

PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding
di: Zhai, Hongjia, et al.
Pubblicazione: (2025)