paper-with-me

Papers

Zero in on Shape: A Generic 2D-3D Instance Similarity Metric learned from Synthetic Data

2021-08-09 · Maciej Janik, Niklas Gard, Anna Hilsmann, Peter Eisert

We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape. Our system is optimised for zero-shot retrieval, meaning it can recognise shapes never shown in training. We use a view-based shape descriptor and a siamese network to learn object geometry from pairs of 3D models and 2D images. Due to scarcity of datasets with exact photograph-mesh correspondences, we train our network with only synthetic data. Our experiments investigate the effect of different qualities and quantities of training data on retrieval accuracy and present insights from bridging the domain gap. We show that increasing the variety of synthetic data improves retrieval accuracy and that our system's performance in zero-shot mode can match that of the instance-aware mode, as far as narrowing down the search to the top 10% of objects.

📄 PDF Abstract BibTeX arXiv:2108.04091

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Methods 이 논문이 사용한 방법론

Siamese Network 설명 없음

Similar Papers 제목 키워드 기반

Fine-Tuned but Zero-Shot 3D Shape Sketch View Similarity and Retrieval

2023-06-14 · Gianluca Berardi, Yulia Gryaditskaya

Recently, encoders like ViT (vision transformer) and ResNet have been trained on vast datasets and utilized as perceptual metrics for comparing sketches and images, as well as multi-domain encoders in a zero-shot setting…

Contrastive LearningRetrieval

Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion

2026-05-25 · Dmytro Klepachevskyi, Alexander Wong, Sirisha Rambhatla, Yuhao Chen arxiv

Object re-identification (ReID) in egocentric kitchen videos is challenging due to rapid viewpoint changes, frequent occlusions, cluttered scenes, and large intra-class appearance variations. Objects may leave and re-ent…

Optimizing Multi-Modal Models for Image-Based Shape Retrieval: The Role of Pre-Alignment and Hard Contrastive Learning

2026-03-07 · Paul Julius Kühn, Cedric Spengler, Michael Weinmann, Arjan Kuijper 외 arxiv

Image-based shape retrieval (IBSR) aims to retrieve 3D models from a database given a query image, hence addressing a classical task in computer vision, computer graphics, and robotics. Recent approaches typically rely o…

3D Shape ClassificationContrastive LearningMetric LearningPoint Clouds

Learning Shape Abstractions by Assembling Volumetric Primitives

2016-12-01 · CVPR 2017 7 · Shubham Tulsiani, Hao Su, Leonidas J. Guibas, Alexei A. Efros 외

We present a learning framework for abstracting complex shapes by learning to assemble objects using 3D volumetric primitives. In addition to generating simple and geometrically interpretable explanations of 3D objects, …

Multiple-Instance Learning by Boosting Infinitely Many Shapelet-based Classifiers

2018-11-20 · Daiki Suehiro, Kohei Hatano, Eiji Takimoto, Shuji Yamamoto 외

We propose a new formulation of Multiple-Instance Learning (MIL). In typical MIL settings, a unit of data is given as a set of instances called a bag and the goal is to find a good classifier of bags based on similarity …

Multiple Instance LearningTime SeriesTime Series AnalysisTime Series Classification