Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 42편

Objaverse-XL

Objaverse-XL 설명 보기

Objaverse-XL is an extensive dataset containing over 10 million 3D objects. This compilation includes a diverse range of 3D objects sourced from various origins: 1. Manually Designed Objects: These are objects created by human designers. 2. Photogrammetry Scans: These scans capture landmarks, everyday items, and even professional scans of historic and antique artifacts. 3. Professional Scans: These scans provide detailed representations of historical and valuable objects. The dataset was developed collaboratively by researchers from institutions such as the Allen Institute for AI, University of Washington, Columbia University, Stability AI, LAION, and Caltech¹²³. It's a treasure trove for exploring and advancing 3D modeling, generation, and understanding. Whether you're interested in training models or experimenting with 3D applications, Objaverse-XL offers a rich resource for your endeavors. (1) Objaverse-XL. https://objaverse.allenai.org/. (2) Objaverse-XL: A Universe of 10M+ 3D Objects - Papers With Code. https://paperswithcode.com/paper/objaverse-xl-a-universe-of-10m-3d-objects. (3) [2307.05663] Objaverse-XL: A Universe of 10M+ 3D Objects - arXiv.org. https://arxiv.org/abs/2307.05663. (4) allenai/objaverse-xl · Datasets at Hugging Face. https://huggingface.co/datasets/allenai/objaverse-xl. (5) Objaverse-XL: A Universe of 10M+ 3D Objects. https://papers.nips.cc/paper_files/paper/2023/hash/70364304877b5e767de4e9a2a511be0c-Abstract-Datasets_and_Benchmarks.html.

관련 논문 1편

BS-Objaverse

BS-Objaverse 설명 보기

BS-Objaverse 660k Dataset is a set of GPT4-Vision-powered multi-modal captions data. It is constructed to enhance modality alignment and fine-grained visual concept perception for describing detailed information about the shape, texture of Objaverse 3D object.