{"url":"/dataset/las-t-large-shape-texture-dataset","name":"LAS&T: Large Shape & Texture Dataset","full_name":"LAS&T: Large Shape & Texture Dataset","description_markdown":"Large Shape and Texture dataset (LAS&T) is a giant dataset of shapes and textures for tasks of  visual shapes and textures identification and  retrieval from single image.\r\n\r\nLAS&T is the largest and most diverse dataset for shape, texture and material recognition and retrieval in 2D and 3D with 650,000 images, based on real world shapes and textures\r\n\r\n## Overview\r\nThe LAS&T Dataset aims to test the most basic aspect of vision in the most general way. Mainly the ability to identify any shape, texture, and material in any setting and environment, without being limited to specific types or classes of objects, materials, and environments. For shapes, this means identifying and retrieving any shape in 2D or 3D with every element of the shape changed between images, including the shape material and texture, orientation, size, and environment. For textures and materials, the goal is to recognize the same texture or material when appearing on different objects, environments, and light conditions. The dataset relies on shapes, textures, and materials extracted from real-world images, leading to an almost unlimited quantity and diversity of real-world natural patterns. Each section of the dataset (shapes, and textures), contains 3D parts that rely on physics-based scenes with realistic light materials and object simulation and abstract 2D parts. In addition, the real-world benchmark for 3D shapes.\r\n\r\n## The dataset divided to several parts\r\n3D shape recognition and retrieval.\r\n\r\n2D shape recognition and retrieval.\r\n\r\n3D Materials recognition and retrieval.\r\n\r\n2D Texture recognition and retrieval.\r\n\r\nEach can be used independently for training and testing.\r\n\r\nAdditional assets are a set of 350,000 natural 2D shapes extracted from real-world images\r\n\r\n3D shape recognition real-world images benchmark","description_withheld":null,"homepage":"https://sites.google.com/view/lastdataset/home","introduced_date":"2024-02-07","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC0","url":null},"modalities":[],"tasks":[{"name":"3D Shape Reconstruction","url":"/task/3d-shape-reconstruction","datasets_with_task":"/datasets/task/3d-shape-reconstruction"},{"name":"3D Object Retrieval","url":"/task/3d-object-retrieval","datasets_with_task":"/datasets/task/3d-object-retrieval"},{"name":"Material Recognition","url":"/task/material-recognition","datasets_with_task":"/datasets/task/material-recognition"},{"name":"3D Shape Recognition","url":"/task/3d-shape-recognition","datasets_with_task":"/datasets/task/3d-shape-recognition"},{"name":"Texture Image Retrieval","url":"/task/texture-image-retrieval-1","datasets_with_task":"/datasets/task/texture-image-retrieval-1"},{"name":"3D Shape Retrieval","url":"/task/3d-shape-retrieval-1","datasets_with_task":"/datasets/task/3d-shape-retrieval-1"}],"languages":[],"variants":["LAS&T: Large Shape & Texture Dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}