Search Results for author: Giuseppe Valenzise

Found 11 papers, 9 papers with code

Lossless Coding of Point Cloud Geometry using a Deep Generative Model

1 code implementation1 Jul 2021 Dat Thanh Nguyen, Maurice Quach, Giuseppe Valenzise, Pierre Duhamel

This paper proposes a lossless point cloud (PC) geometry compression method that uses neural networks to estimate the probability distribution of voxel occupancy.

Arithmetic Data Augmentation

Multiscale deep context modeling for lossless point cloud geometry compression

2 code implementations20 Apr 2021 Dat Thanh Nguyen, Maurice Quach, Giuseppe Valenzise, Pierre Duhamel

We propose a practical deep generative approach for lossless point cloud geometry compression, called MSVoxelDNN, and show that it significantly reduces the rate compared to the MPEG G-PCC codec.

A deep perceptual metric for 3D point clouds

1 code implementation25 Feb 2021 Maurice Quach, Aladine Chetouani, Giuseppe Valenzise, Frederic Dufaux

In addition, we propose a novel truncated distance field voxel grid representation and find that it leads to sparser latent spaces and loss functions that are more correlated with perceived visual quality compared to a binary representation.

Ultra-low bitrate video conferencing using deep image animation

1 code implementation1 Dec 2020 Goluck Konuko, Giuseppe Valenzise, Stéphane Lathuilière

In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications.

Image Animation Video Compression

Learning-based lossless compression of 3D point cloud geometry

1 code implementation30 Nov 2020 Dat Thanh Nguyen, Maurice Quach, Giuseppe Valenzise, Pierre Duhamel

On the one hand, octree representation can eliminate the sparsity in the point cloud.


Improved Deep Point Cloud Geometry Compression

2 code implementations16 Jun 2020 Maurice Quach, Giuseppe Valenzise, Frederic Dufaux

Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc.

Autonomous Driving Mixed Reality

Folding-based compression of point cloud attributes

1 code implementation11 Feb 2020 Maurice Quach, Giuseppe Valenzise, Frederic Dufaux

However, as this mapping process is lossy in nature, we propose several strategies to refine it so that attributes can be mapped to the 2D grid with minimal distortion.

Representation Learning

Potential of deep features for opinion-unaware, distortion-unaware, no-reference image quality assessment

1 code implementation27 Nov 2019 Subhayan Mukherjee, Giuseppe Valenzise, Irene Cheng

However, majority of such methods either use hand-crafted features or require training on human opinion scores (supervised learning), which are difficult to obtain and standardise.

No-Reference Image Quality Assessment

Deep Tone Mapping Operator for High Dynamic Range Images

no code implementations12 Aug 2019 Aakanksha Rana, Praveer Singh, Giuseppe Valenzise, Frederic Dufaux, Nikos Komodakis, Aljosa Smolic

In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output.

Tone Mapping

Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression

2 code implementations20 Mar 2019 Maurice Quach, Giuseppe Valenzise, Frederic Dufaux

Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions.

Mixed Reality Quantization

Learning Local Distortion Visibility From Image Quality Data-sets

no code implementations11 Mar 2018 Navaneeth Kamballur Kottayil, Giuseppe Valenzise, Frederic Dufaux, Irene Cheng

In this paper, we explore a different perspective, and we investigate whether it is possible to learn local distortion visibility from image quality scores.

Local Distortion

Cannot find the paper you are looking for? You can Submit a new open access paper.