paper-with-me

Papers

ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery

2024-06-10 · Xian Sun, Qiwei Yan, Chubo Deng, Chenglong Liu, Yi Jiang, Zhongyan Hou, Wanxuan Lu, Fanglong Yao, Xiaoyu Liu, Lingxiang Hao, Hongfeng Yu

Scene Graph Generation (SGG) is a high-level visual understanding and reasoning task aimed at extracting entities (such as objects) and their interrelationships from images. Significant progress has been made in the study of SGG in natural images in recent years, but its exploration in the domain of remote sensing images remains very limited. The complex characteristics of remote sensing images necessitate higher time and manual interpretation costs for annotation compared to natural images. The lack of a large-scale public SGG benchmark is a major impediment to the advancement of SGG-related research in aerial imagery. In this paper, we introduce the first publicly available large-scale, million-level relation dataset in the field of remote sensing images which is named as ReCon1M. Specifically, our dataset is built upon Fair1M and comprises 21,392 images. It includes annotations for 859,751 object bounding boxes across 60 different categories, and 1,149,342 relation triplets across 64 categories based on these bounding boxes. We provide a detailed description of the dataset's characteristics and statistical information. We conducted two object detection tasks and three sub-tasks within SGG on this dataset, assessing the performance of mainstream methods on these tasks.

📄 PDF Abstract BibTeX arXiv:2406.06028

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Generationobject-detectionObject DetectionRelationScene Graph Generation

Similar Papers 제목 키워드 기반

FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction

2021-11-01 · Hao Zhu, Haotian Yang, Longwei Guo, Yidi Zhang 외

In this paper, we present a large-scale detailed 3D face dataset, FaceScape, and the corresponding benchmark to evaluate single-view facial 3D reconstruction. By training on FaceScape data, a novel algorithm is proposed …

3D Face Reconstruction3D ReconstructionFace Reconstruction

Multi-view 3D Reconstruction with Transformer

2021-03-24 · Dan Wang, Xinrui Cui, Xun Chen, Zhengxia Zou 외

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction an…

3D Object Reconstruction3D ReconstructionMulti-View 3D ReconstructionObject Reconstruction

Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models

2026-03-15 · Diego Royo, Brandon Zhao, Adolfo Muñoz, Diego Gutierrez 외 arxiv

Galaxy clusters are powerful probes of astrophysics and cosmology through gravitational lensing: the clusters' mass, dominated by 85% dark matter, distorts background light. Yet, mass reconstruction lacks the scalability…

ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping

2025-04-15 · CVPR 2025 1 · Shun Iwase, Zubair Irshad, Katherine Liu, Vitor Guizilini 외

Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions.…

3D ReconstructionPose PredictionRobotic Graspingvalid

A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction

2023-01-17 · ICCV 2023 1 · Chongshan Lu, Fukun Yin, Xin Chen, Tao Chen 외

Neural Radiance Fields (NeRF) has achieved impressive results in single object scene reconstruction and novel view synthesis, which have been demonstrated on many single modality and single object focused indoor scene da…

NeRFNovel View SynthesisSurface Reconstruction