Multi-view Convolutional Neural Networks for 3D Shape Recognition
- Hang Su, Subhransu Maji, E. Kalogerakis, E. Learned-Miller
- Computer ScienceIEEE International Conference on Computer Vision
- 5 May 2015
This work presents a standard CNN architecture trained to recognize the shapes' rendered views independently of each other, and shows that a 3D shape can be recognized even from a single view at an accuracy far higher than using state-of-the-art3D shape descriptors.
Learning 3D mesh segmentation and labeling
- E. Kalogerakis, Aaron Hertzmann, Karan Singh
- Computer ScienceACM Transactions on Graphics
- 26 July 2010
This paper presents a data-driven approach to simultaneous segmentation and labeling of parts in 3D meshes, formulated as a Conditional Random Field model, with terms assessing the consistency of faces with labels, and terms between labels of neighboring faces.
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
- Hang Su, V. Jampani, J. Kautz
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 22 February 2018
A network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice that outperforms existing state-of-the-art techniques on 3D segmentation tasks.
MakeItTalk: Speaker-Aware Talking Head Animation
- Yang Zhou, Dingzeyu Li, Xintong Han, E. Kalogerakis, Eli Shechtman, J. Echevarria
- Computer ScienceACM Transactions on Graphics
- 27 April 2020
A method that generates expressive talking heads from a single facial image with audio as the only input that is able to synthesize photorealistic videos of entire talking heads with full range of motion and also animate artistic paintings, sketches, 2D cartoon characters, Japanese mangas, stylized caricatures in a single unified framework.
3D Shape Segmentation with Projective Convolutional Networks
- E. Kalogerakis, Melinos Averkiou, Subhransu Maji, S. Chaudhuri
- Computer ScienceComputer Vision and Pattern Recognition
- 8 December 2016
This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts that significantly outperforms the existing state-of-the-art methods in the currently largest segmentation benchmark (ShapeNet).
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
- Z. Lun, Matheus Gadelha, E. Kalogerakis, Subhransu Maji, Rui Wang
- Computer ScienceInternational Conference on 3D Vision
- 20 July 2017
We propose a method for reconstructing 3D shapes from 2D sketches in the form of line drawings. Our method takes as input a single sketch, or multiple sketches, and outputs a dense point cloud…
CSGNet: Neural Shape Parser for Constructive Solid Geometry
- Gopal Sharma, Rishabh Goyal, Difan Liu, E. Kalogerakis, Subhransu Maji
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 22 December 2017
A neural architecture that takes as input a 2D or 3D shape and outputs a program that generates the shape that is more effective as a shape detector compared to existing state-of-the-art detection techniques and can be trained on novel datasets without ground-truth program annotations through policy gradient techniques.
RisQ: recognizing smoking gestures with inertial sensors on a wristband
- A. Parate, Meng-Chieh Chiu, Chaniel Chadowitz, Deepak Ganesan, E. Kalogerakis
- Computer ScienceACM SIGMOBILE International Conference on Mobile…
- 2 June 2014
RisQ is a mobile solution that leverages a wristband containing a 9-axis inertial measurement unit to capture changes in the orientation of a person's arm, and a machine learning pipeline that processes this data to accurately detect smoking gestures and sessions in real-time.
A probabilistic model for component-based shape synthesis
- E. Kalogerakis, S. Chaudhuri, D. Koller, V. Koltun
- Computer ScienceACM Transactions on Graphics
- 1 July 2012
A new generative model of component-based shape structure is presented, which represents probabilistic relationships between properties of shape components, and relates them to learned underlying causes of structural variability within the domain.
Learning Local Shape Descriptors from Part Correspondences with Multiview Convolutional Networks
- Haibin Huang, E. Kalogerakis, S. Chaudhuri, Duygu Ceylan, Vladimir G. Kim, Ersin Yumer
- Computer ScienceACM Transactions on Graphics
- 14 June 2017
A new local descriptor for 3D shapes is presented, directly applicable to a wide range of shape analysis problems such as point correspondences, semantic segmentation, affordance prediction, and shape-to-scan matching by a convolutional network trained to embed geometrically and semantically similar points close to one another in descriptor space.
...
...