no code implementations • 3 Apr 2024 • Amine Ouasfi, Adnane Boukhayma
Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio.
no code implementations • 20 Nov 2023 • Amine Ouasfi, Adnane Boukhayma
While current state-of-the-art generalizable implicit neural shape models rely on the inductive bias of convolutions, it is still not entirely clear how properties emerging from such biases are compatible with the task of 3D reconstruction from point cloud.
1 code implementation • journal 2023 • Xiaoyuan Wang, Yang Li, Adnane Boukhayma, Changbo Wang, Marc Christie
Reconstructing the shape of hand-held objects from single-view color images is a long-standing problem in computer vision and computer graphics.
1 code implementation • 10 Aug 2022 • Shubhendu Jena, Franck Multon, Adnane Boukhayma
We also perform competitively with respect to the state-of-the-art method SVS, which has been trained on the full dataset (DTU and Tanks and Temples) and then scene finetuned, in spite of their deeper neural renderer.
no code implementations • 24 Jul 2022 • Qian Li, Franck Multon, Adnane Boukhayma
We explore a new strategy for few-shot novel view synthesis based on a neural light field representation.
1 code implementation • 9 Jul 2022 • Amine Ouasfi, Adnane Boukhayma
We explore a new idea for learning based shape reconstruction from a point cloud, based on the recently popularized implicit neural shape representations.
no code implementations • 9 Nov 2021 • Shubhendu Jena, Franck Multon, Adnane Boukhayma
We propose to improve on graph convolution based approaches for human shape and pose estimation from monocular input, using pixel-aligned local image features.
no code implementations • 3 Sep 2021 • Jean Basset, Adnane Boukhayma, Stefanie Wuhrer, Franck Multon, Edmond Boyer
We consider the problem of human deformation transfer, where the goal is to retarget poses between different characters.
no code implementations • 23 Mar 2021 • Nitika Verma, Adnane Boukhayma, Jakob Verbeek, Edmond Boyer
Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids.
1 code implementation • CVPR 2020 • Victoria Fernandez Abrevaya, Adnane Boukhayma, Philip H. S. Torr, Edmond Boyer
Core to our approach is a novel module that we call deactivable skip connections, which allows integrating both the auto-encoded and image-to-normal branches within the same architecture that can be trained end-to-end.
no code implementations • 21 Feb 2019 • Botos Csaba, Adnane Boukhayma, Viveka Kulharia, András Horváth, Philip H. S. Torr
Standard adversarial training involves two agents, namely a generator and a discriminator, playing a mini-max game.
no code implementations • ICCV 2019 • Victoria Fernandez Abrevaya, Adnane Boukhayma, Stefanie Wuhrer, Edmond Boyer
Data-driven generative 3D face models are used to compactly encode facial shape data into meaningful parametric representations.
2 code implementations • CVPR 2019 • Adnane Boukhayma, Rodrigo de Bem, Philip H. S. Torr
We present in this work the first end-to-end deep learning based method that predicts both 3D hand shape and pose from RGB images in the wild.
Ranked #10 on 3D Hand Pose Estimation on FreiHAND (PA-MPVPE metric)
no code implementations • 17 Apr 2018 • Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, Adnane Boukhayma, N. Siddharth, Philip Torr
However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility.
no code implementations • CVPR 2017 • Adnane Boukhayma, Jean-Sebastien Franco, Edmond Boyer
We address the problem of transferring motion between captured 4D models.