Sarah Fachada

Dr. Sarah Fachada

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
27 October 2021 in IEEE Access
Verified
Journal Article
Open access
DBDaniele Bonatto
Daniele Bonatto
SFSarah Fachada
Sarah Fachada
SRSégolène Rogge
Ségolène Rogge
Adrian MunteanuAdrian Munteanu
Adrian Munteanu
GLGauthier Lafruit
Gauthier Lafruit
This paper presents a novel approach to provide immersive free navigation with 6 Degrees of Freedom in real-time for natural and virtual scenery, for both static and dynamic content. Stemming from the state-of-the-art in Depth Image-Based Rendering and the OpenGL pipeline, this new View Synthesis method achieves free navigation at up to 90 FPS and can take any number of input views with their corresponding depth maps as priors. Video content can be played thanks to GPU decompression, supporting free navigation with full parallax in real-time. To render a novel viewpoint, each selected input view is warped using the camera pose and associated depth map, using an implicit 3D representation. The warped views are then blended all together to generate the chosen virtual view. Various view blending approaches specifically designed to avoid visual artifacts are compared. Using as few as four input views appears to be an optimal trade-off between computation time and quality, allowing to synthesize high-quality stereoscopic views in real-time, offering a genuine immersive virtual reality experience. Additionally, the proposed approach provides high-quality rendering of a 3D scenery on holographic light field displays. Our results are comparable - objectively and subjectively - to the state of the art view synthesis tools NeRF and LLFF, while maintaining an overall lower complexity and real-time rendering.

1 June 2018
Verified
Conference Paper
Closed access
SFSarah Fachada
Sarah Fachada
DBDaniele Bonatto
Daniele Bonatto
ASArnaud Schenkel
Arnaud Schenkel
GLGauthier Lafruit
Gauthier Lafruit
This paper presents a method for view synthesis from multiple views and their depth maps for free navigation in Virtual Reality with six degrees of freedom (6DoF) and 360 video (3DoF+), including synthesizing views corresponding to stepping in or out of the scene. Such scenarios should support large baseline view synthesis, typically going beyond the view synthesis involved in light field displays [1]. Our method allows to input an unlimited number of reference views, instead of the usual left and right reference views. Increasing the number of reference views overcomes problems such as occlusions, tangential surfaces to the cameras axis and artifacts in low quality depth maps. We outperform MPEG's reference software, VSRS [2], with a gain of up to 2.5 dB in PSNR when using four reference views.

26 January 2020 in Electronic Imaging
Verified
Journal Article
Open access
DBDaniele Bonatto
Daniele Bonatto
SFSarah Fachada
Sarah Fachada
GLGauthier Lafruit
Gauthier Lafruit
Fast track article for IS&T International Symposium on Electronic Imaging 2020: The Engineering Reality of Virtual Reality proceedings.

1 December 2018
Verified
Conference Paper
Closed access
ASArnaud Schenkel
Arnaud Schenkel
DBDaniele Bonatto
Daniele Bonatto
SFSarah Fachada
Sarah Fachada
HGHenry-Louis Guillaume
Henry-Louis Guillaume
GLGauthier Lafruit
Gauthier Lafruit
Depth Image-Based Rendering (DIBR) and 6 Degrees-of-Freedom (6DoF) navigation are actually very active fields for immersive video, where the availability of common test conditions is mandatory to compare results. For this purpose, we propose different datasets to evaluate a wide range of tools needed by free navigation: a high-density HD image set, composed of 80k camera positions covering the entire 3D space, necessary to simulate all the head rotations and translations of a common user, and a UHD video set, composed of two sequences acquired with 3 by 5 cameras array. All the processing pipeline to obtain quality results is also detailed.

30 November 2020 in Applied Optics
Verified
Journal Article
Closed access
SFSarah Fachada
Sarah Fachada
DBDaniele Bonatto
Daniele Bonatto
GLGauthier Lafruit
Gauthier Lafruit
To computer-generate high-quality holographic stereograms, a huge number of images must be provided: several hundred for a horizontal parallax and the square of this number for a full parallax. In this paper, we propose to drastically reduce this number to four input images with depth maps (or equivalently, four groups of neighboring images used to compute a depth map) in any pose, in order to create the missing images with depth image-based rendering. We evaluate the view synthesis method objectively before providing visual results of the corresponding holographic stereograms. We believe this method outperforms shearlet-based approaches in objective view synthesis quality metrics and in the number of required input images (7×7).

1 December 2018
Verified
Conference Paper
Closed access
SFSarah Fachada
Sarah Fachada
DBDaniele Bonatto
Daniele Bonatto
ASArnaud Schenkel
Arnaud Schenkel
GLGauthier Lafruit
Gauthier Lafruit
MPEG-I standardizing Depth Image-Based Rendering for 6 Degrees of Freedom (6DoF) Free Navigation (limited range, aka 3DoF+) in immersive video is currently exploring two candidate software tools, called respectively VSRS and RVS. The paper shows that for synthesizing virtual views in-between existing camera views in linear/planar camera arrangements, both tools have similar performances, within 0.5 dB in PSNR. For non-linear or 2D camera setups, however, as well as for step-in/out Free Navigation scenarios, RVS outperforms VSRS with up to 2 dB, while also showing aesthetically more pleasant visual results than VSRS.