A large-scale Shape Benchmark for 3D object retrieval: Toyohashi shape benchmark

By Atsushi Tatsuma, Hitoshi Koyanagi, Masaki Aono. 2012

58 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

ShapeNet: An Information-Rich 3D Model Repository (2015, methodology): “(function+form) ESB CAD 867 45 19 Table 1. Source datasets from SHREC 2014: Princeton Shape Benchmark (PSB) [27], SHREC 2012 generic Shape Benchmark (SHREC12GTB) [16], Toyohashi Shape Benchmark (TSB) [29], Konstanz 3D Model Benchmark (CCCC) [32], Watertight Model Benchmark (WMB) [31], McGill 3D Shap”
VisDA: The Visual Domain Adaptation Challenge (2017, methodology): “These four sources include manually chosen subsets of ShapenetCore [4], NTU 3D [5], SHREC 2010 [49] with some labels retrieved from TSB [44] and our own collection of 3D CAD models from 3D Warehouse SketchUp.”
VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation (2018, methodology): “These four sources include manually chosen subsets of ShapenetCore [3], NTU 3D [4], SHREC 2010 [23] with some labels retrieved from TSB [21] and our own collection of 3D CAD models from 3D Warehouse SketchUp.”
GIFT: A Real-Time and Scalable 3D Shape Search Engine (2016, methodology): “We train CNN on an independent TSB dataset [36], and then use the trained CNN to extract view features for the shapes in all the three testing datasets.”
Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols (2015, background): “8 Toyohashi shape benchmark [25] 2012 Mesh models Object retrieval 10k / 352 No http://www.”
Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items (2022, methodology): “3D object datasets suitable for simulation research include those composed of 3D CAD models [41], [26], [42], [43], [44], [45], [11], [12], [13] and 3D scanned models [14], [46], [47], [48], [49], [15], [16], [50], [51] though many combine types [47].”
SHREC'14 Track: Large Scale Comprehensive 3D Shape Retrieval (2014, unknown): “…Princeton Shape Benchmark ( PSB ) [SMKF04], the SHREC’12 Generic Track Benchmark ( SHREC12GTB ) [LGA ∗ 12], the Toyohashi Shape Benchmark ( TSB ) [TKA12], the Konstanz 3D Model Benchmark ( CCCC ) [Vra04], the Watertight Model Benchmark ( WMB ) [VtH07], the McGill 3D Shape Benchmark ( MSB ) [SZM…”
Recent Trends, Applications, and Perspectives in 3D Shape Similarity Assessment (2016, methodology): “…, in part building on the Princeton Shape Benchmark but speciﬁcally designed for non-rigid shape retrieval [SZM*08]; the Toyohashi Shape Benchmark [TKA12], consisting of 10,000 3D models grouped in 352 classes; the NTU 3D model database [CTSO03] consisting of 10,911 models that can be used to…”
The YCB object and Model set: Towards common benchmarks for manipulation research (2015, background): “[1, 2, 4, 12-15]) that provide mesh model datasets of objects, these datasets have limited utility for manipulation benchmarking due to several reasons: First, since most of them are not designed specifically for manipulation benchmarking, the selected objects do not usually cover the shape variety ”