no code implementations • 26 Apr 2024 • Alice Gao, Samyukta Jayakumar, Marcello Maniglia, Brian Curless, Ira Kemelmacher-Shlizerman, Aaron R. Seitz, Steven M. Seitz
We consider the question of how to best achieve the perception of eye contact when a person is captured by camera and then rendered on a 2D display.
no code implementations • 6 Nov 2023 • Vivek Jayaram, Ira Kemelmacher-Shlizerman, Steven M. Seitz
Our approach offers an efficient and accessible method for deriving personalized HRTFs and has the potential to greatly improve spatial audio experiences.
no code implementations • 12 Oct 2023 • Mengyi Shan, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz
We present a system that automatically brings street view imagery to life by populating it with naturally behaving, animated pedestrians and vehicles.
no code implementations • 28 Aug 2023 • Bowei Chen, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz
We present a method to generate full-body selfies from photographs originally taken at arms length.
1 code implementation • CVPR 2023 • Luyang Zhu, Dawei Yang, Tyler Zhu, Fitsum Reda, William Chan, Chitwan Saharia, Mohammad Norouzi, Ira Kemelmacher-Shlizerman
Given two images depicting a person and a garment worn by another person, our goal is to generate a visualization of how the garment might look on the input person.
no code implementations • 12 Apr 2023 • Johanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher-Shlizerman
We fine-tune on a collection of fashion videos from the UBC Fashion dataset.
no code implementations • CVPR 2023 • Chung-Yi Weng, Pratul P. Srinivasan, Brian Curless, Ira Kemelmacher-Shlizerman
We present PersonNeRF, a method that takes a collection of photos of a subject (e. g. Roger Federer) captured across multiple years with arbitrary body poses and appearances, and enables rendering the subject with arbitrary novel combinations of viewpoint, body pose, and appearance.
no code implementations • ICCV 2023 • Johanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher-Shlizerman
We fine-tune on a collection of fashion videos from the UBC Fashion dataset.
1 code implementation • CVPR 2022 • Chung-Yi Weng, Brian Curless, Pratul P. Srinivasan, Jonathan T. Barron, Ira Kemelmacher-Shlizerman
Our method optimizes for a volumetric representation of the person in a canonical T-pose, in concert with a motion field that maps the estimated canonical representation to every frame of the video via backward warps.
1 code implementation • CVPR 2022 • Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong Joon Park, Ira Kemelmacher-Shlizerman
We introduce a high resolution, 3D-consistent image and shape generation technique which we call StyleSDF.
no code implementations • ICCV 2021 • Soumyadip Sengupta, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz
Whereas existing light stages require expensive, room-scale spherical capture gantries and exist in only a few labs in the world, we demonstrate how to acquire useful data from a normal TV or desktop monitor.
4 code implementations • 6 Jan 2021 • Kathleen M Lewis, Srivatsan Varadharajan, Ira Kemelmacher-Shlizerman
Previous methods mostly focused on texture transfer via paired data training, while overlooking body shape deformations, skin color, and seamless blending of garment with the person.
no code implementations • 23 Dec 2020 • Chung-Yi Weng, Brian Curless, Ira Kemelmacher-Shlizerman
At the core of our method is a volumetric 3D human representation reconstructed with a deep network trained on input video, enabling novel pose/view synthesis.
2 code implementations • CVPR 2021 • Shanchuan Lin, Andrey Ryabtsev, Soumyadip Sengupta, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman
We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU.
1 code implementation • NeurIPS 2020 • Teerapat Jenrungrot, Vivek Jayaram, Steve Seitz, Ira Kemelmacher-Shlizerman
Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers.
2 code implementations • ECCV 2020 • Luyang Zhu, Konstantinos Rematas, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman
Based on these models, we introduce a new method that takes as input a single photo of a clothed player in any basketball pose and outputs a high resolution mesh and 3D pose for that player.
1 code implementation • CVPR 2020 • Soumyadip Sengupta, Vivek Jayaram, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman
To bridge the domain gap to real imagery with no labeling, we train another matting network guided by the first network and by a discriminator that judges the quality of composites.
Ranked #1 on Image Matting on Adobe Matting
2 code implementations • ECCV 2020 • Roy Or-El, Soumyadip Sengupta, Ohad Fried, Eli Shechtman, Ira Kemelmacher-Shlizerman
Most existing aging methods are limited to changing the texture, overlooking transformations in head shape that occur during the human aging and growth process.
no code implementations • CVPR 2019 • Chung-Yi Weng, Brian Curless, Ira Kemelmacher-Shlizerman
The key contributions of this paper are: 1) an application of viewing and animating humans in single photos in 3D, 2) a novel 2D warping method to deform a posable template body model to fit the person's complex silhouette to create an animatable mesh, and 3) a method for handling partial self occlusions.
no code implementations • 13 Sep 2018 • Shu Liang, Xiufeng Huang, Xianyu Meng, Kunyao Chen, Linda G. Shapiro, Ira Kemelmacher-Shlizerman
In this paper, we describe a system that can completely automatically create a reconstruction from any video (even a selfie video), and we don't require specific views, since taking your -90 degree, 90 degree, and full back views is not feasible in a selfie capture.
no code implementations • 13 Sep 2018 • Shu Liang, Ira Kemelmacher-Shlizerman, Linda G. Shapiro
We further combine the input depth frame with the matched database shapes into a single mesh that results in a high-resolution shape of the input person.
no code implementations • 13 Sep 2018 • Shu Liang, Linda G. Shapiro, Ira Kemelmacher-Shlizerman
Our method is to gradually "grow" the head mesh starting from the frontal face and extending to the rest of views using photometric stereo constraints.
no code implementations • CVPR 2018 • Konstantinos Rematas, Ira Kemelmacher-Shlizerman, Brian Curless, Steve Seitz
We present a system that transforms a monocular video of a soccer game into a moving 3D reconstruction, in which the players and field can be rendered interactively with a 3D viewer or through an Augmented Reality device.
1 code implementation • CVPR 2018 • Eli Shlizerman, Lucio M. Dery, Hayden Schoen, Ira Kemelmacher-Shlizerman
We present a method that gets as input an audio of violin or piano playing, and outputs a video of skeleton predictions which are further used to animate an avatar.
no code implementations • CVPR 2017 • Aaron Nech, Ira Kemelmacher-Shlizerman
Some key discoveries: 1) algorithms, trained on MF2, were able to achieve state of the art and comparable results to algorithms trained on massive private sets, 2) some outperformed themselves once trained on MF2, 3) invariance to aging suffers from low accuracies as in MegaFace, identifying the need for larger age variations possibly within identities or adjustment of algorithms in future testings.
no code implementations • CVPR 2016 • Ira Kemelmacher-Shlizerman, Steve Seitz, Daniel Miller, Evan Brossard
Our key observations are that testing at the million scale reveals big performance differences (of algorithms that perform similarly well on smaller scale) and that age invariant recognition as well as pose are still challenging for most.
no code implementations • ICCV 2015 • Supasorn Suwajanakorn, Steven M. Seitz, Ira Kemelmacher-Shlizerman
We reconstruct a controllable model of a person from a large photo collection that captures his or her persona, i. e., physical appearance and behavior.
no code implementations • 2 Jun 2015 • Supasorn Suwajanakorn, Ira Kemelmacher-Shlizerman, Steve Seitz
We reconstruct a controllable model of a person from a large photo collection that captures his or her {\em persona}, i. e., physical appearance and behavior.
no code implementations • CVPR 2014 • Ira Kemelmacher-Shlizerman, Supasorn Suwajanakorn, Steven M. Seitz
We present an approach that takes a single photograph of a child as input and automatically produces a series of age-progressed outputs between 1 and 80 years of age, accounting for pose, expression, and illumination.