← Search

Louis Chevallier

4 accepted papers

2021

Towards High Fidelity Monocular Face Reconstruction With Rich Reflectance Using Self-Supervised Learning and Ray Tracing

ICCV 2021poster

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, lighting and reflectance. They can also be trained i…

Cited by 56PDFcodeScholar
2019

SoDeep: A Sorting Deep Net to Learn Ranking Loss Surrogates

CVPR 2019oral

Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Surrogate and relaxation methods exist but tend to be…

Cited by 90PDFcodeScholar
2018

Finding Beans in Burgers: Deep Semantic-Visual Embedding With Localization

CVPR 2018poster

Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships. Such a multi-modal embedding can be trained and used for various tasks, notably image captioning. In the pr…

2015

Hybrid multi-layer deep CNN/aggregator feature for image classification

ICASSP 2015accepted

Deep Convolutional Neural Networks (DCNN) have established a remarkable performance benchmark in the field of image classification, displacing classical approaches based on hand-tailored aggregations of local descriptors. Yet DCNNs impose high computational burdens both at training and at testing ti…

Cited by 0SourceScholar