Matthieu FRADET

Dr. Matthieu FRADET

InterDigital
orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2014 in SIAM Journal on Imaging Sciences
Verified
Journal Article
Closed access
ANAlasdair Newson
Alasdair Newson
AAAndrés Almansa
Andrés Almansa
Matthieu FRADETMatthieu FRADET
Matthieu FRADET
YGYann Gousseau
Yann Gousseau
PPPatrick Pérez
Patrick Pérez
We propose an automatic video inpainting algorithm which relies on the optimization of a global, patch-based functional. Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects, and moving background. Furthermore, we achieve this in an order of magnitude less execution time with respect to the state-of-the-art. We are also able to achieve good quality results on high-definition videos. Finally, we provide specific algorithmic details to make implementation of our algorithm as easy as possible. The resulting algorithm requires no segmentation or manual input other than the definition of the inpainting mask and can deal with a wider variety of situations than is handled by previous work.

6 November 2013
Verified
Conference Paper
Open access
PDF file
ANAlasdair Newson
Alasdair Newson
AAAndrés Almansa
Andrés Almansa
Matthieu FRADETMatthieu FRADET
Matthieu FRADET
YGYann Gousseau
Yann Gousseau
PPPatrick Pérez
Patrick Pérez

1 November 2009
Verified
Conference Paper
Closed access
Matthieu FRADETMatthieu FRADET
Matthieu FRADET
PRPhilippe Robert
Philippe Robert
PPPatrick Pérez
Patrick Pérez
Motion-based segmentation of a sequence of images is an essential step for many applications of video analysis, including action recognition and surveillance. This paper introduces a new approach to motion segmentation operating on point trajectories. Each of these trajectories has its own start and end instants, hence its own life-span, depending on the pose and appearance changes of the object it belongs to. A set of such trajectories is obtained by tracking sparse interest points. Based on an adaptation of recently proposed J-linkage method, these trajectories are then clustered using series of affine motion models estimated between consecutive instants, and an appropriate residual that can handle trajectories with various life-spans. Our approach does not require any completion of trajectories whose life-span is shorter than the sequence of interest. We evaluate the performance of the single cue of motion, without considering spatial prior and appearance. Using a standard test set, we validate our new algorithm and compare it to existing ones. Experimental results on a variety of challenging real sequences demonstrate the potential of our approach.

1 October 2018
Verified
Conference Paper
Closed access
GQGlen Queguiner
Glen Queguiner
Matthieu FRADETMatthieu FRADET
Matthieu FRADET
MRMohammad Rouhani
Mohammad Rouhani
We present a diminished reality application running live on consumer mobile devices. In our pre-observation-based approach, the clean 3D scene, free of undesired objects, is scanned beforehand and reconstructed as a high resolution textured 3D model. At runtime, objects added in a region of interest are efficiently removed by projecting the previously captured background. Differences of illumination conditions between scan time and run-time are compensated to obtain seamless results. The proposed approach requires no segmentation or manual input other than the definition of the 3D region of interest to be diminished, and is not based on any particular assumption on the background geometry. We show the potential of our approach by processing a variety of challenging unknown 3D scenes including textured backgrounds, dynamic illumination conditions and foreground objects partially occluding the diminished region. We provide details on our compute shader implementation to make as easy as possible the reimplementation by the community.

8 July 2014 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
TCTomas Crivelli
Tomas Crivelli
Matthieu FRADETMatthieu FRADET
Matthieu FRADET
PCPierre-Henri Conze
Pierre-Henri Conze
PRPhilippe Robert
Philippe Robert
PPPatrick Perez
Patrick Perez
We analyze the problem of how to correctly construct dense point trajectories from optical flow fields. First, we show that simple Euler integration is unavoidably inaccurate, no matter how good is the optical flow estimator. Then, an inverse integration scheme is analyzed which is more robust to bias and input noise and shows better stability properties. Our contribution is threefold: 1) a theoretical analysis that demonstrates why and in what sense inverse integration is more accurate; 2) a rich experimental validation both on synthetic and real (image) data; and 3) an algorithm for approximate online inverse integration. This new technique is precious whether one is trying to propagate information densely available on a reference frame to the other frames in the sequence or, conversely, to assign information densely over each frame by pulling it from the reference.

8 November 2017
Verified
Conference Paper
Open access
PDF file
CBCaroline Baillard
Caroline Baillard
Matthieu FRADETMatthieu FRADET
Matthieu FRADET
VAVincent Alleaume
Vincent Alleaume
PJPierrick Jouet
Pierrick Jouet
ALAnthony Laurent
Anthony Laurent