paper-with-me

Papers

LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories

2023-11-20 · Silvan Weder, Hermann Blum, Francis Engelmann, Marc Pollefeys

Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generate labels for RGB-D scans at equal (or better) level of accuracy than comparable manually annotated datasets such as ScanNet. Our approach is based on an ensemble of state-of-the-art segmentation models and 3D lifting through neural rendering. We demonstrate the effectiveness of our LabelMaker pipeline by generating significantly better labels for the ScanNet datasets and automatically labelling the previously unlabeled ARKitScenes dataset. Code and models are available at https://labelmaker.org

📄 PDF Abstract BibTeX arXiv:2311.12174

Code (1)

cvg/labelmaker 공식 구현 pytorch

Tasks

Neural RenderingSemantic Segmentation

Similar Papers 제목 키워드 기반

ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding

2024-10-17 · CVPR 2025 1 · Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys 외

The performance of neural networks scales with both their size and the amount of data they have been trained on. This is shown in both language and image generation. However, this requires scaling-friendly network archit…

3D Semantic SegmentationImage GenerationScene UnderstandingSemantic Segmentation

Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis

2023-05-19 · Mario Giulianelli, Iris Luden, Raquel Fernandez, Andrey Kutuzov

We propose using automatically generated natural language definitions of contextualised word usages as interpretable word and word sense representations. Given a collection of usage examples for a target word, and the co…

Language ModelingLanguage ModellingSemantic SimilaritySemantic Textual Similarity+2

Automatic Generation of a Lexical Resource to support Semantic Role Labeling in Portuguese

2015-06-01 · SEMEVAL 2015 6 · Magali Sanches Duran, S Alu{\'\i}sio, ra
Semantic Role Labeling

A Semantic Role-based Approach to Open-Domain Automatic Question Generation

2018-06-01 · WS 2018 6 · Michael Flor, Brian Riordan

We present a novel rule-based system for automatic generation of factual questions from sentences, using semantic role labeling (SRL) as the main form of text analysis. The system is capable of generating both wh-questio…

Dependency ParsingQuestion GenerationQuestion-GenerationReading Comprehension+1

Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization

2026-03-19 · Shiyan Liu, Qifeng Xia, Qiyun Xia, Yisheng Liu 외 arxiv

Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iteratively refine prompts by diagnosing failure…

Prompt Engineering