Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Ahn, Junghyun"'
A deep learning system typically suffers from a lack of reproducibility that is partially rooted in hardware or software implementation details. The irreproducibility leads to skepticism in deep learning technologies and it can hinder them from being
Externí odkaz:
http://arxiv.org/abs/2410.09872
There have been recent efforts to learn more meaningful representations via fixed length codewords from mesh data, since a mesh serves as a complete model of underlying 3D shape compared to a point cloud. However, the mesh connectivity presents new d
Externí odkaz:
http://arxiv.org/abs/2308.15413
We present a novel face reconstruction method capable of reconstructing detailed face geometry, spatially varying face reflectance from a single monocular image. We build our work upon the recent advances of DNN-based auto-encoders with differentiabl
Externí odkaz:
http://arxiv.org/abs/2203.07732
Autor:
Ahn, Junghyun
Three studies were conducted to better inform how instructional design of educational programming for children impacts learning. In these studies, we focused on how unplugged debugging activities, which require correction of coding errors, affect ski
Autor:
Damodaran, Bharath Bhushan, Jolly, Emmanuel, Puy, Gilles, Gosselin, Philippe Henri, Thébault, Cédric, Ahn, Junghyun, Christensen, Tim, Ghezzo, Paul, Hellier, Pierre
Publikováno v:
European Conference on Visual Media Production (CVMP '21), 2021
We present FacialFilmroll, a solution for spatially and temporally consistent editing of faces in one or multiple shots. We build upon unwrap mosaic [Rav-Acha et al. 2008] by specializing it to faces. We leverage recent techniques to fit a 3D face mo
Externí odkaz:
http://arxiv.org/abs/2110.02124
Autor:
Dib, Abdallah, Thebault, Cedric, Ahn, Junghyun, Gosselin, Philippe-Henri, Theobalt, Christian, Chevallier, Louis
Robust face reconstruction from monocular image in general lighting conditions is challenging. Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular reconstruction of geometry, li
Externí odkaz:
http://arxiv.org/abs/2103.15432
Autor:
Dib, Abdallah, Bharaj, Gaurav, Ahn, Junghyun, Thébault, Cédric, Gosselin, Philippe-Henri, Romeo, Marco, Chevallier, Louis
We present a differentiable ray-tracing based novel face reconstruction approach where scene attributes - 3D geometry, reflectance (diffuse, specular and roughness), pose, camera parameters, and scene illumination - are estimated from unconstrained m
Externí odkaz:
http://arxiv.org/abs/2101.05356
Autor:
Dib, Abdallah, Bharaj, Gaurav, Ahn, Junghyun, Thebault, Cedric, Gosselin, Philippe-Henri, Chevallier, Louis
We present a novel strategy to automatically reconstruct 3D faces from monocular images with explicitly disentangled facial geometry (pose, identity and expression), reflectance (diffuse and specular albedo), and self-shadows. The scene lights are mo
Externí odkaz:
http://arxiv.org/abs/1910.05200
Publikováno v:
In LWT 1 March 2023 177
Autor:
Ahn, Junghyun
Thesis (S.M.)--Massachusetts Institute of Technology, System Design and Management Program, 2008.
Includes bibliographical references (p. 50).
The emergence of composite material application in major commercial aircraft design, represented
Includes bibliographical references (p. 50).
The emergence of composite material application in major commercial aircraft design, represented
Externí odkaz:
http://hdl.handle.net/1721.1/43106