ObjectNet3D: A Large Scale Database for 3D Object Recognition (2016) ġ00 categories, 90,127 images, 201,888 objects in these images and 44,147 3D shapes. ShapeNetCore : 51300 models for 55 categories.Ī Large Dataset of Object Scans (2016) ġ0K scans in RGBD + reconstructed 3D models in. A dataset that is large in scale, well organized and richly annotated. ModelNet40: 12311 models from 40 categories, all are uniformly orientatedģMillion+ models and 4K+ categories. ModelNet10: 4899 models from 10 categories Our annotation framework draws on crowdsourcing to segment surfaces from photos, and then annotate them with rich surface properties, including material, texture and contextual information.ġ2 categories, on average 3k+ objects per category, for 3D object detection and pose estimation. OpenSurfaces is a large database of annotated surfaces created from real-world consumer photographs. Open Surfaces: A Richly Annotated Catalog of Surface Appearance (SIGGRAPH 2013) Used to evaluating shape-based retrieval and analysis algorithms.ĭataset for IKEA 3D models and aligned images (2013) ħ59 images and 219 models including Sketchup (skp) and Wavefront (obj) files, good for pose estimation. 3D Modelsġ,814 models collected from the web in. Point Cloud Library also has a good dataset catalogue. To see a survey of RGBD datasets, check out Michael Firman's collection as well as the associated paper, RGBD Datasets: Past, Present and Future. Princeton CS597: Geometric Modeling and Analysis (Fall 2003)ĬreativeAI: Deep Learning for Graphics Datasets Princeton COS 526: Advanced Computer Graphics (Fall 2010) Stanford CS468: Machine Learning for 3D Data (Spring 2017) UCSD CSE291-I00: Machine Learning for 3D Data (Winter 2018) Stanford CS231A: Computer Vision-From 3D Reconstruction to Recognition (Winter 2018)
To contribute to this Repo, you may add content through pull requests or open an issue to let me know.
To find related papers and their relationships, check out Connected Papers, which provides a neat way to visualize the academic field in a graph representation. I'll use the following icons to differentiate 3D representations:
This repo is derived from my study notes and will be used as a place for triaging new research papers. In recent years, tremendous amount of progress is being made in the field of 3D Machine Learning, which is an interdisciplinary field that fuses computer vision, computer graphics and machine learning.