paper-with-me

Papers

3DRef: 3D Dataset and Benchmark for Reflection Detection in RGB and Lidar Data

2024-03-11 · Xiting Zhao, Sören Schwertfeger

Reflective surfaces present a persistent challenge for reliable 3D mapping and perception in robotics and autonomous systems. However, existing reflection datasets and benchmarks remain limited to sparse 2D data. This paper introduces the first large-scale 3D reflection detection dataset containing more than 50,000 aligned samples of multi-return Lidar, RGB images, and 2D/3D semantic labels across diverse indoor environments with various reflections. Textured 3D ground truth meshes enable automatic point cloud labeling to provide precise ground truth annotations. Detailed benchmarks evaluate three Lidar point cloud segmentation methods, as well as current state-of-the-art image segmentation networks for glass and mirror detection. The proposed dataset advances reflection detection by providing a comprehensive testbed with precise global alignment, multi-modal data, and diverse reflective objects and materials. It will drive future research towards reliable reflection detection. The dataset is publicly available at http://3dref.github.io

📄 PDF Abstract BibTeX arXiv:2403.06538

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationMirror DetectionPoint Cloud SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction

2025-10-04 · Yue Huang, Yanyuan Chen, Dexuan Xu, Chenzhuo Zhao 외 arxiv

Medical problem-solving demands expert knowledge and intricate reasoning. Recent studies of large language models (LLMs) attempt to ease this complexity by introducing external knowledge verification through retrieval-au…

WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language

2023-04-12 · Zhenxiang Lin, Xidong Peng, Peishan Cong, Ge Zheng 외

We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images and 3D LiDAR point clouds. We present a…

3D visual groundingAutonomous DrivingObject LocalizationVisual Grounding

3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects

2026-05-11 · Zhicheng Liang, Haoyi Yu, Boyan Li, Dayou Zhang 외 arxiv

Accurate 3D reconstruction of objects with reflective, transparent, or low-texture surfaces still remains notoriously challenging. Such materials often violate key assumptions in multi-view reconstruction pipelines, such…

Novel View SynthesisReflection Removal3D ReconstructionImage Matching

Beyond Reflection: Affirmation as a Promising Behavioral Marker Associated with Quality in Text-Based Counseling

2026-08-27 · Michimasa Inaba arxiv

While AI-assisted text-based counseling is gaining attention, it remains empirically unclear which counselor behaviors are associated with higher dialogue quality. Existing research often focuses heavily on Reflection, b…

Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal

2026-03-30 · Kazuma Ikeda, Ryosei Hara, Rokuto Nagata, Ozora Sako. Zihao Ding 외 arxiv

LiDAR has become an essential sensing modality in autonomous driving, robotics, and smart-city applications. However, ghost points (or ghosts), which are false reflections caused by multi-path laser returns from glass an…

Representation Learning3D Object DetectionAutonomous DrivingPoint Clouds