We propose Scan2Part, a method to segment individual parts of objects in...
We present a new multi-sensor dataset for 3D surface reconstruction. It
...
Depth maps captured with commodity sensors often require super-resolutio...
We present a pipeline for parametric wireframe extraction from densely
s...
Depth maps captured with commodity sensors are often of low quality and
...
Recent advances in 3D semantic scene understanding have shown impressive...
Sharp feature lines carry essential information about human-made objects...
Estimation of differential geometric quantities in discrete 3D data
repr...
DensePose estimation task is a significant step forward for enhancing us...
The video generation task can be formulated as a prediction of future vi...
We present a new method for vectorization of technical line drawings, su...
Constructing high-quality generative models for 3D shapes is a fundament...
Segmentation of tumors in brain MRI images is a challenging task, where ...
Reconstruction of directional fields is a need in many geometry processi...
Data-driven methods such as convolutional neural networks (CNNs) are kno...
Monocular 3D object detection is well-known to be a challenging vision t...
RGBD images, combining high-resolution color and lower-resolution depth ...
We introduce ABC-Dataset, a collection of one million Computer-Aided Des...
As machine learning continues to gain momentum in the neuroscience commu...
We consider a problem of diagnostic pattern recognition/classification f...