Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Jean Mélou

dblp:199/2374 · DBLP profile ↗
← Back
7ranked-venue papers
0as first author
5since 2021 · last 2026
0009-0000-7990-2290ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Graphics, computer vision, multimedia, augmented reality and games · 6 · 4 since 2021Artificial intelligence and machine learning · 2 · 2 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
2 papers
3D vision · 100%
Computer graphics and multimedia
4 papers
Computational photography and imaging · 46% Audio and music processing · 46% Multimedia systems and quality of experience · 8%
Human-computer interaction and pervasive computing
3 papers
Games and playful interaction · 78% Interaction techniques and input · 22%

Topics — the 7 heaviest of 10, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Computer vision › 3D vision
3d reconstruction
1.012026
Multi-view Surface Reconstruction Using Normal and Reflectance Cues · Int. J. Comput. Vis. 2026
Computer vision › 3D vision › 3d reconstruction › surface reconstruction
multi-view surface reconstruction
1.012026
Multi-view Surface Reconstruction Using Normal and Reflectance Cues · Int. J. Comput. Vis. 2026
Computational photography and imaging › intrinsic image decomposition
reflectance and shading
1.012026
Multi-view Surface Reconstruction Using Normal and Reflectance Cues · Int. J. Comput. Vis. 2026
Computer vision › 3D vision › photometric stereo
multi-view photometric stereo
0.812024
RNb-NeuS: Reflectance and Normal-Based Multi-View 3D Reconstruction · CVPR 2024
Computer vision › 3D vision › 3d reconstruction
multi-view reconstruction
0.812024
RNb-NeuS: Reflectance and Normal-Based Multi-View 3D Reconstruction · CVPR 2024
Interaction techniques and input
mobile interaction
0.312025
Transform your Smartphone in a Real-time Sonagram Player · ACM Multimedia 2025
Computer vision › 3D vision › neural rendering
neural volume rendering
0.212024
RNb-NeuS: Reflectance and Normal-Based Multi-View 3D Reconstruction · CVPR 2024

Methods — techniques the papers use, named apart from their topics

reflectance cues · 2.0normal cues · 2.0sonification · 1.7sound encoding · 1.1image encoding · 1.1photometric stereo · 0.8laser sheet interaction · 0.8joint reparameterization · 0.8
YearPublicationVenuePosition
2026 Multi-view Surface Reconstruction Using Normal and Reflectance Cues
Robin Bruneau, Baptiste Brument, Yvain Quéau, Jean Mélou, François Lauze, Jean-Denis Durou, Lilian Calvet
Int. J. Comput. Vis.4
2025 Transform your Smartphone in a Real-time Sonagram Player
abstract
International audience
Jean-Denis Durou, Jean Mélou, Yvain Quéau, Gilles Azzaro, Hugo Pauget Ballesteros, Gabriel Gournay, Achille Jeanvoine, Clément Lacire, Floriane Payen, Julie Remenant
ACM Multimedia2
2025 Assessing the Quality of 3D Reconstruction in the Absence of Ground Truth: Application to a Multimodal Archaeological Dataset
abstract
International audience
Benjamin Coupry, Baptiste Brument, Antoine Laurent, Jean Mélou, Yvain Quéau, Jean-Denis Durou
WACV4
2024 RNb-NeuS: Reflectance and Normal-Based Multi-View 3D Reconstruction
abstract
This paper introduces a versatile paradigm for integrating multi-view reflectance (optional) and normal maps acquired through photometric stereo. Our approach employs a pixel-wise joint reparameterization of reflectance and normal, considering them as a vector of radiances rendered under simulated, varying illumination. This re-parameterization enables the seamless integration of reflectance and normal maps as input data in neural volume rendering-based 3D reconstruction while preserving a single optimization objective. In contrast, recent multi-view photometric stereo (MVPS) methods depend on multiple, potentially conflicting objectives. Despite its apparent simplicity, our proposed approach outperforms state-of-the-art approaches in MVPS benchmarks across F-score, Chamfer distance, and mean angular error metrics. Notably, it significantly improves the detailed 3D reconstruction of areas with high curvature or low visibility.
Baptiste Brument, Robin Bruneau, Yvain Quéau, Jean Mélou, François Lauze, Jean-Denis Durou, Lilian Calvet
CVPR4
2022 Read Your Voice: A Playful Interactive Sound Encoder/Decoder
abstract
Read Your Voice is a playful interactive multimedia system that allows the user to record a sound, encode it as an image, and then play it back using his smartphone, while controlling the speed and direction of playback.
Hugo Pauget Ballesteros, Gilles Azzaro, Jean Mélou, Yvain Quéau, Jean-Denis Durou
ACM Multimedia3
2020 Refractive Multi-view Stereo
abstract
In this article we show how to extend the multi-view stereo technique when the object to be reconstructed is inside a transparent - but refractive - material, which causes distortions in the images. We provide a theoretical formulation of the problem accounting for a general, non-planar shape of the refractive interface, then a discrete solving method, which are validated by tests on synthetic and real data.
Matthew Cassidy, Jean Mélou, Yvain Quéau, François Lauze, Jean-Denis Durou
3DV2
2019 Macrogroove: A Sound 3D-sculpture Interactive Player
abstract
Macrogroove is an interactive and playful multimedia system that allows the user to play a sound coded in the form of a 3D-sonagram. The user is invited to manually move a laser sheet over this "pseudo-relief", in order to playback the original sound in real time.
Paul Chable, Gilles Azzaro, Jean Mélou, Yvain Quéau, Axel Carlier, Jean-Denis Durou
ACM Multimedia3