Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Martin Engelcke

Universal Approximation of Functions on Sets

Jul 05, 2021
Edward Wagstaff, Fabian B. Fuchs, Martin Engelcke, Michael A. Osborne, Ingmar Posner

* 54 pages, 13 figures 

  Access Paper or Ask Questions

APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation

May 31, 2021
Yizhe Wu, Oiwi Parker Jones, Martin Engelcke, Ingmar Posner

* 8 pages, 5 figures 

  Access Paper or Ask Questions

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

Apr 21, 2021
Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

  Access Paper or Ask Questions

Reconstruction Bottlenecks in Object-Centric Generative Models

Jul 13, 2020
Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

* 10 pages, 7 Figures, Workshop on Object-Oriented Learning at ICML 2020 

  Access Paper or Ask Questions

First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotion

Jul 03, 2020
Alexander L. Mitchell, Martin Engelcke, Oiwi Parker Jones, David Surovik, Ioannis Havoutis, Ingmar Posner

* 8 pages, 7 figures, accepted to IROS 2020 

  Access Paper or Ask Questions

RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces

Jul 02, 2020
Sebastien Ehrhardt, Oliver Groth, Aron Monszpart, Martin Engelcke, Ingmar Posner, Niloy Mitra, Andrea Vedaldi

  Access Paper or Ask Questions

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

Jul 30, 2019
Martin Engelcke, Adam R. Kosiorek, Oiwi Parker Jones, Ingmar Posner

* Submitted to the 3rd Conference on Robot Learning (CoRL 2019) 

  Access Paper or Ask Questions

On the Limitations of Representing Functions on Sets

Jan 25, 2019
Edward Wagstaff, Fabian B. Fuchs, Martin Engelcke, Ingmar Posner, Michael Osborne

* Submitted to the International Conference on Machine Learning (2019) for review 

  Access Paper or Ask Questions

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Nov 28, 2017
Benjamin Graham, Martin Engelcke, Laurens van der Maaten

* arXiv admin note: text overlap with arXiv:1706.01307 

  Access Paper or Ask Questions

Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

Oct 27, 2017
Li Yi, Lin Shao, Manolis Savva, Haibin Huang, Yang Zhou, Qirui Wang, Benjamin Graham, Martin Engelcke, Roman Klokov, Victor Lempitsky, Yuan Gan, Pengyu Wang, Kun Liu, Fenggen Yu, Panpan Shui, Bingyang Hu, Yan Zhang, Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Minki Jeong, Jaehoon Choi, Changick Kim, Angom Geetchandra, Narasimha Murthy, Bhargava Ramu, Bharadwaj Manda, M Ramanathan, Gautam Kumar, P Preetham, Siddharth Srivastava, Swati Bhugra, Brejesh Lall, Christian Haene, Shubham Tulsiani, Jitendra Malik, Jared Lafer, Ramsey Jones, Siyuan Li, Jie Lu, Shi Jin, Jingyi Yu, Qixing Huang, Evangelos Kalogerakis, Silvio Savarese, Pat Hanrahan, Thomas Funkhouser, Hao Su, Leonidas Guibas

  Access Paper or Ask Questions

Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks

Mar 05, 2017
Martin Engelcke, Dushyant Rao, Dominic Zeng Wang, Chi Hay Tong, Ingmar Posner

* To be published at the IEEE International Conference on Robotics and Automation 2017 

  Access Paper or Ask Questions