三維中的非常規物體

UnCommon Objects in 3D

January 13, 2025

作者: Xingchen Liu, Piyush Tayal, Jianyuan Wang, Jesus Zarzar, Tom Monnier, Konstantinos Tertikas, Jiali Duan, Antoine Toisoul, Jason Y. Zhang, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, David Novotny

cs.AI

摘要

我們介紹了一個名為Uncommon Objects in 3D (uCO3D)的新物件中心數據集，用於3D深度學習和3D生成人工智慧。uCO3D是最大的公開可用的高分辨率物件影片集合，具有3D標註，確保全方位360度覆蓋。uCO3D比MVImgNet和CO3Dv2更加多樣化，涵蓋超過1,000個物件類別。由於對收集的影片和3D標註進行了廣泛的質量檢查，因此質量更高。與類似的數據集一樣，uCO3D包含了3D相機姿勢、深度圖和稀疏點雲的標註。此外，每個物件都配有標題和3D高斯斑點重建。我們在MVImgNet、CO3Dv2和uCO3D上訓練了幾個大型3D模型，並且使用後者獲得了優越的結果，表明uCO3D對於學習應用更為優越。

English

We introduce Uncommon Objects in 3D (uCO3D), a new object-centric dataset for 3D deep learning and 3D generative AI. uCO3D is the largest publicly-available collection of high-resolution videos of objects with 3D annotations that ensures full-360^{circ} coverage. uCO3D is significantly more diverse than MVImgNet and CO3Dv2, covering more than 1,000 object categories. It is also of higher quality, due to extensive quality checks of both the collected videos and the 3D annotations. Similar to analogous datasets, uCO3D contains annotations for 3D camera poses, depth maps and sparse point clouds. In addition, each object is equipped with a caption and a 3D Gaussian Splat reconstruction. We train several large 3D models on MVImgNet, CO3Dv2, and uCO3D and obtain superior results using the latter, showing that uCO3D is better for learning applications.