no code implementations • CVPR 2014 • Hedi Tabia, Hamid Laga, David Picard, Philippe-Henri Gosselin
We evaluate the performance of the proposed Bag of Covariance Matrices framework on 3D shape matching and retrieval applications and demonstrate its superiority compared to descriptor-based techniques.
no code implementations • 29 Oct 2014 • Ahmet Iscen, Giorgos Tolias, Philippe-Henri Gosselin, Hervé Jégou
Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks.
no code implementations • 27 Nov 2017 • Bharath Bhushan Damodaran, Nicolas Courty, Philippe-Henri Gosselin
Thus, reducing the number of feature dimensions is necessary to effectively scale to large datasets.
no code implementations • 3 Oct 2019 • Abdallah Dib, Gaurav Bharaj, Junghyun Ahn, Cedric Thebault, Philippe-Henri Gosselin, Louis Chevallier
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.
1 code implementation • 13 Jan 2021 • Abdallah Dib, Gaurav Bharaj, Junghyun Ahn, Cédric Thébault, Philippe-Henri Gosselin, Marco Romeo, Louis Chevallier
The proposed method models scene illumination via a novel, parameterized virtual light stage, which in-conjunction with differentiable ray-tracing, introduces a coarse-to-fine optimization formulation for face reconstruction.
1 code implementation • ICCV 2021 • Abdallah Dib, Cedric Thebault, Junghyun Ahn, Philippe-Henri Gosselin, Christian Theobalt, Louis Chevallier
In this paper, we build our work on the aforementioned approaches and propose a new method that greatly improves reconstruction quality and robustness in general scenes.
Ranked #12 on 3D Face Reconstruction on NoW Benchmark
no code implementations • 15 Mar 2022 • Abdallah Dib, Junghyun Ahn, Cedric Thebault, Philippe-Henri Gosselin, Louis Chevallier
We present a novel face reconstruction method capable of reconstructing detailed face geometry, spatially varying face reflectance from a single monocular image.
no code implementations • ICIAP 2022 • Martin Dornier, Philippe-Henri Gosselin, Christian Raymond, Yann Ricquebourg, Bertrand Coüasnon
Supervised face alignment methods need large amounts of training data to achieve good performance in terms of accuracy and generalization.
Ranked #30 on Face Alignment on WFLW
no code implementations • HAL 2022 • Martin Dornier, Philippe-Henri Gosselin, Christian Raymond, Yann Ricquebourg, Bertrand Coüasnon
In this paper, we propose to use StyleGAN to perform face alignment with limited training data instead of image generation.
Ranked #3 on Face Alignment on AFLW-19