List your company

Research

Papers for “semantic segmentation”

Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.

Search results

TitleAuthorsYearSource
Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian SplattingYiren Lu, Xin Ye, Burhaneddin Yaman2026arxiv 2603.19193
Unlocking 3D Affordance Segmentation with 2D Semantic KnowledgeYu Huang, Zelin Peng, Changsong Wen2025arxiv 2510.08316
Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric VideoYuting Tan, Xilong Cheng, Yunxiao Qin2026arxiv 2603.13912
Seeing Beyond: Extrapolative Domain Adaptive Panoramic SegmentationYuanfan Zheng, Kunyu Peng, Xu Zheng2026arxiv 2603.15475
MSSSeg: Learning Multi-Scale Structural Complexity for Self-Supervised SegmentationHaotang Li, Zhenyu Qi, Hao Qin2025arxiv 2512.23997
Elite Lanes: Evolutionary Generation of Realistic Small-Scale Road NetworksArtur Morys-Magiera, Marek D\lugosz, Pawe\l Skruch2026arxiv 2603.20964
Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain GeneralizationHao Li, Yubin Xiao, Ke Liang2025arxiv 2503.13617
UrbanVGGT: Scalable Sidewalk Width Estimation from Street View ImagesKaizhen Tan, Fan Zhang2026arxiv 2603.22531
KeySG: Hierarchical Keyframe-Based 3D Scene GraphsAbdelrhman Werby, Dennis Rotondi, Fabio Scaparro2025arxiv 2510.01049
RTFDNet: Fusion-Decoupling for Robust RGB-T SegmentationKunyu Tan, Mingjian Liang2026arxiv 2603.09149
Unified Restoration-Perception Learning: Maritime Infrared-Visible Image Fusion and SegmentationWeichao Cai, Weiliang Huang, Biao Xue2026arxiv 2603.28414
Excite, Attend and Segment (EASe): Domain-Agnostic Fine-Grained Mask Discovery with Feature Calibration and Self-Supervised UpsamplingDeepank Singh, Anurag Nihal, Vedhus Hoskere2026arxiv 2604.00276
Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth ObservationÜmit Mert Çağlar, Alptekin Temizel2026arxiv 2606.25128
AirTF: Over-the-Air Token Fusion for Task-Oriented Multi-Modal Token CommunicationsBole Liu, Li Qiao, Minghui Wu2026arxiv 2607.03099
Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision TransformersCong Liu, Xiaofang Li, Simon X. Yang2026arxiv 2607.00580
OctoSense: Self-Supervised Learning for Multimodal Robot PerceptionAnthony Bisulco, Jeremy Wang, Kostas Daniilidis2026arxiv 2606.27317
When Less Is More: A Controlled Benchmark of Lightweight CNNs for Satellite Land-Cover Segmentation on DeepGlobeAtiq Ur Rehman, Joseph Michael Donovan2026arxiv 2607.23024
Perturbation-Aware Diffusion-Guided Hybrid Segmentation for Robust and Annotation-Efficient Plant Stress PhenotypingGurbhit Chaurakoti, Soumyashree Kar2026arxiv 2607.23680
ObliCity: A Benchmark and Baseline for Roof-to-Ground Projection Displacement CorrectionKai Li, Yupeng Deng, Ligao Deng2026arxiv 2607.25210
RSV-SLAM: Toward Real-Time Semantic Visual SLAM in Indoor Dynamic EnvironmentsMobin Habibpour, Alireza Nemati, Ali Meghdari2025arxiv 2510.02616