MELON: NeRF with Unposed Images in SO(3)

no code implementations • 14 Mar 2023 • Axel Levy, Mark Matthews, Matan Sela, Gordon Wetzstein, Dmitry Lagun

Neural radiance fields enable novel-view synthesis and scene reconstruction with photorealistic quality from a few images, but require known and accurate camera poses.

Inverse Rendering Novel View Synthesis +1

Kubric: A scalable dataset generator

1 code implementation • CVPR 2022 • Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti, Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi

Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.

Fairness Optical Flow Estimation

Specular-to-Diffuse Translation for Multi-View Reconstruction

no code implementations • ECCV 2018 • Shihao Wu, Hui Huang, Tiziano Portenier, Matan Sela, Danny Cohen-Or, Ron Kimmel, Matthias Zwicker

To alleviate this restriction, we introduce S2Dnet, a generative adversarial network for transferring multiple views of objects with specular reflection into diffuse ones, so that multi-view reconstruction methods can be applied more effectively.

3D Reconstruction Generative Adversarial Network +4

GazeGAN - Unpaired Adversarial Image Generation for Gaze Estimation

no code implementations • 27 Nov 2017 • Matan Sela, Pingmei Xu, Junfeng He, Vidhya Navalpakkam, Dmitry Lagun

Recent research has demonstrated the ability to estimate gaze on mobile devices by performing inference on the image from the phone's front-facing camera, and without requiring specialized hardware.

Gaze Estimation Image Generation +1

Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation

2 code implementations • ICCV 2017 • Matan Sela, Elad Richardson, Ron Kimmel

It has been recently shown that neural networks can recover the geometric structure of a face from a single given image.

3D Face Reconstruction Image-to-Image Translation +1

Learning Detailed Face Reconstruction from a Single Image

no code implementations • CVPR 2017 • Elad Richardson, Matan Sela, Roy Or-El, Ron Kimmel

In contrast, we propose to leverage the power of convolutional neural networks to produce a highly detailed face reconstruction from a single image.

Face Reconstruction Object Recognition

Randomized Independent Component Analysis

no code implementations • 22 Sep 2016 • Matan Sela, Ron Kimmel

Independent component analysis (ICA) is a method for recovering statistically independent signals from observations of unknown linear combinations of the sources.

Customized Facial Constant Positive Air Pressure (CPAP) Masks

no code implementations • 22 Sep 2016 • Matan Sela, Nadav Toledo, Yaron Honen, Ron Kimmel

The incompatibility is characterized by gaps between the mask and the face, which deteriorates the impermeability of the mask and leads to air leakage.

Consistent Discretization and Minimization of the L1 Norm on Manifolds

no code implementations • 18 Sep 2016 • Alex Bronstein, Yoni Choukroun, Ron Kimmel, Matan Sela

The L1 norm has been tremendously popular in signal and image processing in the past two decades due to its sparsity-promoting properties.

3D Face Reconstruction by Learning from Synthetic Data

no code implementations • 14 Sep 2016 • Elad Richardson, Matan Sela, Ron Kimmel

Fast and robust three-dimensional reconstruction of facial geometric structure from a single image is a challenging task with numerous applications.

3D Face Reconstruction