paper-with-me

Papers 3D Semantic Segmentation

“3D Semantic Segmentation” 태그가 달린 논문 391편 · 필터 해제

VLRC: Vision-Language Reprojection Consistency as a scalable signal for better feed-forward 3D pretraining

2026-07-02 · Marwane Hariat, David Filliat, Antoine Manzanera arxiv

Feed-forward 3D models are commonly trained using either expensive geometric supervision or self-supervised photometric objectives, both of which provide incomplete learning signals. We introduce Vision-Language Reprojec…

3D Semantic SegmentationScene Understanding3D Reconstruction

Privacy-Preserving Depth-Only Open-Vocabulary 3D Semantic Segmentation Via Uncertainty-Guided Test-Time Optimization

2026-07-01 · Xuying Huang, Sicong Pan, Maren Bennewitz arxiv

Privacy-preserving perception is a critical requirement for deploying 3D scene understanding systems in real-world indoor environments, yet it remains underexplored in open-vocabulary 3D semantic segmentation. Existing m…

3D Semantic SegmentationScene Understanding

Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation

2026-06-24 · Xiaopei Wu, Yuenan Hou, Junkai Xu, Wenxiao Wang 외 arxiv

Multi-modal fusion and multi-model ensembling are prevalent in enhancing the performance of 3D semantic segmentation. Despite the impressive performance, these methods either rely on auxiliary input signals or suffer fro…

3D Semantic SegmentationKnowledge DistillationPoint Clouds

GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer

2026-05-22 · Diogo Lavado, Alessandra Micheletti, Clàudia Soares arxiv

In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures that are present in the 3D data. However, existing methods lack explicit mechanisms to inc…

3D Semantic SegmentationScene Understanding

Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentation

2026-05-16 · Bin Yang, Alexandru Paul Condurache arxiv

Annotating large-scale LiDAR point clouds for 3D semantic segmentation is costly and time-consuming, which motivates the use of semi-supervised learning (SemiSL). Standard LiDAR SemiSL methods typically adopt a two-step …

LIDAR Semantic Segmentation3D Semantic SegmentationPoint Clouds

OPTNet: Ordering Point Transformer Network for Post-disaster 3D Semantic Segmentation

2026-05-16 · Nhut Le, Ehsan Karimi, Maryam Rahnemoonfar arxiv

Post-disaster damage assessment requires rapid and accurate semantic segmentation of 3D point clouds to identify critical infrastructure such as damaged buildings and roads. Early Point Transformers (e.g., PTv1, PTv2) re…

3D Semantic SegmentationPoint Clouds

UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition

2026-05-08 · Shuai Zhang, Zhecheng Shi, Zhuxiao Li, Jing Ou 외 arxiv

Semantic segmentation of large-scale 3D point clouds is crucial for applications such as autonomous driving and urban digital twins. However, the sparse sampling pattern of LiDAR and the view-dependent geometric distorti…

3D Semantic SegmentationComputational EfficiencyAutonomous DrivingPoint Clouds

FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers

2026-05-05 · Timon Homberger, Finn Lukas Busch, Jesús Gerardo Ortega Peimbert, Quantao Yang 외 arxiv

Open-vocabulary semantic mapping enables robots to spatially ground previously unseen concepts without requiring predefined class sets. Current training-free methods commonly rely on multi-view fusion of semantic embeddi…

3D Semantic Segmentation

INSIGHT: Indoor Scene Intelligence from Geometric-Semantic Hierarchy Transfer for Public~Safety

2026-04-25 · Alexander Nikitas Dimopoulos, Joseph Grasso, John Beltz arxiv

Indoor environments lack the spatial intelligence infrastructure that GPS provides outdoors; first responders arriving at unfamiliar buildings typically have no machine-readable map of safety equipment. Prior work on 3D …

3D Semantic SegmentationPoint Clouds

PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving

2026-04-21 · Yining Pan, Shijie Li, Yuchen Wu, Xulei Yang 외 arxiv

This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world auton…

Unsupervised Domain Adaptation3D Semantic SegmentationRepresentation LearningPanoptic Segmentation

Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding

2026-04-21 · Kadir Yilmaz, Adrian Kruse, Tristan Höfer, Daan de Geus 외 arxiv

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ec…

3D Semantic Segmentation3D Instance SegmentationScene Understanding

Instant Colorization of Gaussian Splats

2026-04-18 · Daniel Lieber, Alexander Mock, Nils Wandel arxiv

Gaussian Splatting has recently become one of the most popular frameworks for photorealistic 3D scene reconstruction and rendering. While current rasterizers allow for efficient mappings of 3D Gaussian splats onto 2D cam…

3D Semantic Segmentation

GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation

2026-03-27 · Xujing Tao, Chuxin Wang, Yubo Ai, Zhixin Cheng 외 arxiv

Open-vocabulary 3D semantic segmentation aims to segment arbitrary categories beyond the training set. Existing methods predominantly rely on distilling knowledge from 2D open-vocabulary models. However, aligning 3D feat…

3D Semantic SegmentationSemantic Similarity

Benchmarking Deep Learning Models for Aerial LiDAR Point Cloud Semantic Segmentation under Real Acquisition Conditions: A Case Study in Navarre

2026-03-23 · Alex Salvatierra, José Antonio Sanz, Christian Gutiérrez, Mikel Galar arxiv

Recent advances in deep learning have significantly improved 3D semantic segmentation, but most models focus on indoor or terrestrial datasets. Their behavior under real aerial acquisition conditions remains insufficient…

3D Semantic SegmentationComputational Efficiency

Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation

2026-03-20 · Yifei Zhao, Fanyu Zhao, Yinsheng Li arxiv

Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with only a few annotated support examples. Existing prototype-based methods typically construct compact and deterministic…

Point Cloud Segmentation3D Semantic SegmentationPoint Clouds

JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramas

2026-03-06 · Sandeep Inuganti, Hideaki Kanayama, Kanta Shimizu, Mahdi Chamseddine 외 arxiv

Semantic segmentation across visual modalities such as 3D point clouds and panoramic images remains a challenging task, primarily due to the scarcity of annotated data and the limited adaptability of fixed-label models. …

Open Vocabulary Semantic Segmentation3D Semantic SegmentationScene UnderstandingPoint Clouds

CoSMo3D: Open-World Promptable 3D Semantic Part Segmentation through LLM-Guided Canonical Spatial Modeling

2026-03-01 · Li Jin, Weikai Chen, Yujie Wang, Yingda Yin 외 arxiv

Open-world promptable 3D semantic segmentation remains brittle as semantics are inferred in the input sensor coordinates. Yet, humans, in contrast, interpret parts via functional roles in a canonical space -- wings exten…

3D Semantic Segmentation

XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation

2026-01-20 · Frank Bieder, Hendrik Königshof, Haohao Hu, Fabian Immel 외 arxiv

Until open-world foundation models match the performance of specialized approaches, deep learning systems remain dependent on task- and sensor-specific data availability. To bridge the gap between available datasets and …

2D Semantic Segmentation2D Panoptic Segmentation3D Semantic SegmentationDomain Adaptation

GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure

2026-01-19 · Antoine Carreaud, Shanci Li, Malo De Lacour, Digre Frinde 외 arxiv

This paper presents GridNet-HD, a multi-modal dataset for 3D semantic segmentation of overhead electrical infrastructures, pairing high-density LiDAR with high-resolution oblique imagery. The dataset comprises 7,694 imag…

3D Semantic Segmentation

Deep Learning for Semantic Segmentation of 3D Ultrasound Data

2026-01-19 · Chenyu Liu, Marco Cecotti, Harikrishnan Vijayakumar, Patrick Robinson 외 arxiv

Developing cost-efficient and reliable perception systems remains a central challenge for automated vehicles. LiDAR and camera-based systems dominate, yet they present trade-offs in cost, robustness and performance under…

3D Semantic Segmentation
1–20 / 391 다음 →