17 skills found
paschalidoud / Neural PartsCode for "Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks", CVPR 2021
shubhtuls / VolumetricPrimitivesCode release for "Learning Shape Abstractions by Assembling Volumetric Primitives " (CVPR 2017)
ChirikjianLab / Marching Primitives[CVPR2023 Highlight] Marching-Primitives: Shape Abstraction from Signed Distance Function
SilenKZYoung / CuboidAbstractionViaSegThis repo is a PyTorch implementation for Paper "Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds"
fkluger / Cuboids RevisitedRobust Shape Fitting for 3D Scene Abstraction
isunchy / Cuboid AbstractionCode release for "Learning Adaptive Hierarchical Cuboid Abstractions of 3D Shape Collections" (SIGGRAPH Asia 2019)
threedle / Wir3dOfficial implementation of "WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction"
lodurality / GEM3D Paper CodeCode for GEM3D: Generative Medial Abstractions for 3D Shape Synthesis
Stanford-ILIAD / ELLAReward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.
regar007 / ShapesInOpenGLES2.0Create basic shapes in opnegles2. And for abstraction purpose, its a class implementation using VBO's to create basic shapes in Open GLES2.0
FisherYuuri / Marching Primitives PythonThis is an unofficial version of the python code for Marching-Primitives: Shape Abstraction from Signed Distance Function
bhosmer / FoldUnified multidimensional array model that collects nonrectangular shapes, advanced indexing, views and sparsity into a single set of composable abstractions Resources
BardOfCodes / SuperfitFit compact primitive assemblies (SuperFrusta, cuboids, superquadrics) to 3D shapes via residual fitting. CVPR 2026.
Wu-Yuwei / Shape Abstraction Via Superquadric[ECCV2022] Primitive-based Shape Abstraction via Nonparametric Bayesian Inference
aditya-vora / HiTHiT: Hierarchical Transformers for Unsupervised 3D Shape Abstraction
unlin / LibbwabstractionCode for the paper "Scale-aware Black-and-White Abstraction of 3D Shapes" in SIGGRAPH 2018.
21arunava / Content Based Image RetreivalThe aim of this project is to review the current state of the art in content-based image retrieval (CBIR), a technique for retrieving images on the basis of automatically-derived features such as color, texture and shape. My findings are primary based both on a review of the relevant literature and on exploring possible enhancements over the net.The need to find a desired image from a collection is shared by many professional groups, including journalists, design engineers and art historians. While the requirements of image users can vary considerably, it can be useful to characterize image queries into three levels of abstraction: primitive features such as color or shape, logical features such as the identity of objects shown and abstract attributes such as the significance of the scenes depicted. While CBIR systems currently operate effectively only at the lowest of these levels, most users demand higher levels of retrieval.
