|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
We study 3D shape modeling from a single image and make contributions to it in three aspects.
SOTA for 3D Shape Retrieval on Pix3D
Intrinsic graph convolution operators with differentiable kernel functions play a crucial role in analyzing 3D shape meshes.
To solve this, we propose Implicit Feature Networks (IF-Nets), which deliver continuous outputs, can handle multiple topologies, and complete shapes for missing or sparse input data retaining the nice properties of recent learned implicit functions, but critically they can also retain detail when it is present in the input data, and can reconstruct articulated humans.
We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances.
The recent success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to 3D shapes.
This method not only allows us to analytically and compactly represent the object, it also confers on us the ability to overcome calibration related noise that originates from inaccurate acquisition parameters.
We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll.