D. Ceylan

Publications
Influence

A scalable active framework for region annotation in 3D shape collections

L. Yi, Vladimir G. Kim, +7 authors L. Guibas
Computer Science
ACM Trans. Graph.
11 November 2016

We propose a novel active learning method capable of enriching massive geometric datasets with accurate semantic region annotations. Expand

BodyNet: Volumetric Inference of 3D Human Body Shapes

G. Varol, D. Ceylan, +4 authors C. Schmid
Computer Science
ECCV
13 April 2018

BodyNet is an end-to-end trainable network that benefits from (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision. Expand

Transformation-Grounded Image Generation Network for Novel 3D View Synthesis

Eunbyung Park, Jimei Yang, Ersin Yumer, D. Ceylan, A. Berg
Mathematics, Computer Science
IEEE Conference on Computer Vision and Pattern…
8 March 2017

We present a transformation-grounded image generation network for novel 3D view synthesis from a single image. Expand

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB Images

C. Zimmermann, D. Ceylan, Jimei Yang, Bryan C. Russell, Max Argus, T. Brox
Computer Science
IEEE/CVF International Conference on Computer…
10 September 2019

We introduce the first large-scale, multi-view hand dataset that is accompanied by both 3D hand pose and shape annotations. Expand

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

Qiangeng Xu, Weiyue Wang, D. Ceylan, R. Mech, U. Neumann
Computer Science
NeurIPS
26 May 2019

We present DISN, a Deep Implicit Surface Network which can generate a high-quality detail-rich 3D mesh from an 2D image by predicting the underlying signed distance fields. Expand

PlaneNet: Piece-Wise Planar Reconstruction from a Single RGB Image

C. Liu, Jimei Yang, D. Ceylan, Ersin Yumer, Y. Furukawa
Computer Science
IEEE/CVF Conference on Computer Vision and…
17 April 2018

This paper proposes a deep neural network (DNN) for piece-wise planar depthmap reconstruction from a single RGB image. Expand

Dense Human Body Correspondences Using Convolutional Networks

Lingyu Wei, Qixing Huang, D. Ceylan, Etienne Vouga, Hao Li
Computer Science
IEEE Conference on Computer Vision and Pattern…
18 November 2015

We use a deep convolutional neural network to train a feature descriptor on depth map pixels, but crucially, rather than training the network to solve the shape correspondence problem directly, we train it to solve a body region classification problem. Expand

Learning Local Shape Descriptors from Part Correspondences with Multiview Convolutional Networks

Haibin Huang, E. Kalogerakis, S. Chaudhuri, D. Ceylan, Vladimir G. Kim, Ersin Yumer
Computer Science
ACM Trans. Graph.
14 June 2017

We present a new local descriptor for 3D shapes, directly applicable to a wide range of shape analysis problems such as point correspondence, semantic segmentation, affordance prediction, and shape-to-scan matching. Expand

3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks

Chuhang Zou, Ersin Yumer, Jimei Yang, D. Ceylan, Derek Hoiem
Computer Science, Mathematics
IEEE International Conference on Computer Vision…
4 August 2017

The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Expand

Material Editing Using a Physically Based Rendering Network

Guilin Liu, D. Ceylan, Ersin Yumer, Jimei Yang, J. Lien
Computer Science
IEEE International Conference on Computer Vision…
1 August 2017

We present an end-to-end network architecture for image-based material editing that replicates the image formation process in a physically based rendering layer. Expand

Recommended Authors