Eduardo Pavéz
YOU?
Author Swipe
View article: Adaptive Voxelization for Transform coding of 3D Gaussian splatting data
Adaptive Voxelization for Transform coding of 3D Gaussian splatting data Open
We present a novel compression framework for 3D Gaussian splatting (3DGS) data that leverages transform coding tools originally developed for point clouds. Contrary to existing 3DGS compression methods, our approach can produce compressed …
View article: Rate-Distortion Optimization with Non-Reference Metrics for UGC Compression
Rate-Distortion Optimization with Non-Reference Metrics for UGC Compression Open
Service providers must encode a large volume of noisy videos to meet the demand for user-generated content (UGC) in online video-sharing platforms. However, low-quality UGC challenges conventional codecs based on rate-distortion optimizati…
View article: Joint Optimization of Primary and Secondary Transforms Using Rate-Distortion Optimized Transform Design
Joint Optimization of Primary and Secondary Transforms Using Rate-Distortion Optimized Transform Design Open
Data-dependent transforms are increasingly being incorporated into next-generation video coding systems such as AVM, a codec under development by the Alliance for Open Media (AOM), and VVC. To circumvent the computational complexities asso…
View article: Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization
Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization Open
Many images and videos are primarily processed by computer vision algorithms, involving only occasional human inspection. When this content requires compression before processing, e.g., in distributed applications, coding methods must opti…
View article: Towards joint graph learning and sampling set selection from data
Towards joint graph learning and sampling set selection from data Open
We explore the problem of sampling graph signals in scenarios where the graph structure is not predefined and must be inferred from data. In this scenario, existing approaches rely on a two-step process, where a graph is learned first, fol…
View article: Color-Guided Flying Pixel Correction in Depth Images
Color-Guided Flying Pixel Correction in Depth Images Open
We present a novel method to correct flying pixels within data captured by Time-of-flight (ToF) sensors. Flying pixel (FP) artifacts occur when signals from foreground and background objects reach the same sensor pixel, leading to a confid…
View article: Graph-based Scalable Sampling of 3D Point Cloud Attributes
Graph-based Scalable Sampling of 3D Point Cloud Attributes Open
3D Point clouds (PCs) are commonly used to represent 3D scenes. They can have millions of points, making subsequent downstream tasks such as compression and streaming computationally expensive. PC sampling (selecting a subset of points) ca…
View article: Graph-Based Signal Sampling with Adaptive Subspace Reconstruction for Spatially-Irregular Sensor Data
Graph-Based Signal Sampling with Adaptive Subspace Reconstruction for Spatially-Irregular Sensor Data Open
Choosing an appropriate frequency definition and norm is critical in graph signal sampling and reconstruction. Most previous works define frequencies based on the spectral properties of the graph and use the same frequency definition and $…
View article: Fast DCT+: A Family of Fast Transforms Based on Rank-One Updates of the Path Graph
Fast DCT+: A Family of Fast Transforms Based on Rank-One Updates of the Path Graph Open
This paper develops fast graph Fourier transform (GFT) algorithms with O(n log n) runtime complexity for rank-one updates of the path graph. We first show that several commonly-used audio and video coding transforms belong to this class of…
View article: Feature-Preserving Rate-Distortion Optimization in Image Coding for Machines
Feature-Preserving Rate-Distortion Optimization in Image Coding for Machines Open
With the increasing number of images and videos consumed by computer vision algorithms, compression methods are evolving to consider both perceptual quality and performance in downstream tasks. Traditional codecs can tackle this problem by…
View article: Full reference point cloud quality assessment using support vector regression
Full reference point cloud quality assessment using support vector regression Open
Point clouds are a general format for representing realistic 3D objects in diverse 3D applications. Since point clouds have large data sizes, developing efficient point cloud compression methods is crucial. However, excessive compression l…
View article: Full-reference Point Cloud Quality Assessment Using Spectral Graph Wavelets
Full-reference Point Cloud Quality Assessment Using Spectral Graph Wavelets Open
Point clouds in 3D applications frequently experience quality degradation during processing, e.g., scanning and compression. Reliable point cloud quality assessment (PCQA) is important for developing compression algorithms with good bitrat…
View article: Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures
Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures Open
We present new results to model and understand the role of encoder-decoder design in machine learning (ML) from an information-theoretic angle. We use two main information concepts, information sufficiency (IS) and mutual information loss …
View article: Adaptive Online Learning of Separable Path Graph Transforms for Intra-prediction
Adaptive Online Learning of Separable Path Graph Transforms for Intra-prediction Open
Current video coding standards, including H.264/AVC, HEVC, and VVC, employ discrete cosine transform (DCT), discrete sine transform (DST), and secondary to Karhunen-Loeve transforms (KLTs) decorrelate the intra-prediction residuals. Howeve…
View article: Fast graph-based denoising for point cloud color information
Fast graph-based denoising for point cloud color information Open
Point clouds are utilized in various 3D applications such as cross-reality (XR) and realistic 3D displays. In some applications, e.g., for live streaming using a 3D point cloud, real-time point cloud denoising methods are required to enhan…
View article: Irregularity-Aware Bandlimited Approximation for Graph Signal Interpolation
Irregularity-Aware Bandlimited Approximation for Graph Signal Interpolation Open
In most work to date, graph signal sampling and reconstruction algorithms are intrinsically tied to graph properties, assuming bandlimitedness and optimal sampling set choices. However, practical scenarios often defy these assumptions, lea…
View article: Joint Graph and Vertex Importance Learning
Joint Graph and Vertex Importance Learning Open
In this paper, we explore the topic of graph learning from the perspective of\nthe Irregularity-Aware Graph Fourier Transform, with the goal of learning the\ngraph signal space inner product to better model data. We propose a novel\nmethod…
View article: HEMATOLOGICAL AND SERUM CHEMISTRY REFERENCE VALUES OF CAPTIVE BLACK-CHESTED BUZZARD EAGLE (GERANOETUS MELANOLEUCUS)
HEMATOLOGICAL AND SERUM CHEMISTRY REFERENCE VALUES OF CAPTIVE BLACK-CHESTED BUZZARD EAGLE (GERANOETUS MELANOLEUCUS) Open
30 captive Black-chested Buzzard-Eagles (Geranoetus melanoleucus) from the Raptors Rehabilitation Center of the Union of Ornithologists of Chile, were used to determine reference values. Packed cell volume (PCV), total protein plasma (TPP)…
View article: Joint Graph and Vertex Importance Learning
Joint Graph and Vertex Importance Learning Open
In this paper, we explore the topic of graph learning from the perspective of the Irregularity-Aware Graph Fourier Transform, with the goal of learning the graph signal space inner product to better model data. We propose a novel method to…
View article: Rate-Distortion Optimization With Alternative References For UGC Video Compression
Rate-Distortion Optimization With Alternative References For UGC Video Compression Open
User generated content (UGC) refers to videos that are uploaded by users and shared over the Internet. UGC may have low quality due to noise and previous compression. When re-encoding UGC for streaming or downloading, a traditional video c…
View article: Image Coding via Perceptually Inspired Graph Learning
Image Coding via Perceptually Inspired Graph Learning Open
Most codec designs rely on the mean squared error (MSE) as a fidelity metric in rate-distortion optimization, which allows to choose the optimal parameters in the transform domain but may fail to reflect perceptual quality. Alternative dis…
View article: Two Channel Filter Banks on Arbitrary Graphs With Positive Semi Definite Variation Operators
Two Channel Filter Banks on Arbitrary Graphs With Positive Semi Definite Variation Operators Open
International audience
View article: Motion estimation and filtered prediction for dynamic point cloud attribute compression
Motion estimation and filtered prediction for dynamic point cloud attribute compression Open
In point cloud compression, exploiting temporal redundancy for inter predictive coding is challenging because of the irregular geometry. This paper proposes an efficient block-based inter-coding scheme for color attribute compression. The …
View article: Learning Sparse Graph with Minimax Concave Penalty under Gaussian Markov Random Fields
Learning Sparse Graph with Minimax Concave Penalty under Gaussian Markov Random Fields Open
This paper presents a convex-analytic framework to learn sparse graphs from data. While our problem formulation is inspired by an extension of the graphical lasso using the so-called combinatorial graph Laplacian framework, a key differenc…
View article: Compression of user generated content using denoised references
Compression of user generated content using denoised references Open
Video shared over the internet is commonly referred to as user generated content (UGC). UGC video may have low quality due to various factors including previous compression. UGC video is uploaded by users, and then it is re-encoded to be m…
View article: Two Channel Filter Banks on Arbitrary Graphs with Positive Semi Definite Variation Operators
Two Channel Filter Banks on Arbitrary Graphs with Positive Semi Definite Variation Operators Open
We propose novel two-channel filter banks for signals on graphs. Our designs can be applied to arbitrary graphs, given a positive semi definite variation operator, while using arbitrary vertex partitions for downsampling. The proposed gene…
View article: Fractional Motion Estimation for Point Cloud Compression
Fractional Motion Estimation for Point Cloud Compression Open
Motivated by the success of fractional pixel motion in video coding, we explore the design of motion estimation with fractional-voxel resolution for compression of color attributes of dynamic 3D point clouds. Our proposed block-based fract…
View article: Laplacian Constrained Precision Matrix Estimation: Existence and High Dimensional Consistency
Laplacian Constrained Precision Matrix Estimation: Existence and High Dimensional Consistency Open
This paper considers the problem of estimating high dimensional Laplacian constrained precision matrices by minimizing Stein's loss. We obtain a necessary and sufficient condition for existence of this estimator, that consists on checking …
View article: Laplacian Constrained Precision Matrix Estimation: Existence and High\n Dimensional Consistency
Laplacian Constrained Precision Matrix Estimation: Existence and High\n Dimensional Consistency Open
This paper considers the problem of estimating high dimensional Laplacian\nconstrained precision matrices by minimizing Stein's loss. We obtain a\nnecessary and sufficient condition for existence of this estimator, that\nconsists on checki…
View article: Learning Sparse Graph with Minimax Concave Penalty under Gaussian Markov Random Fields
Learning Sparse Graph with Minimax Concave Penalty under Gaussian Markov Random Fields Open
This paper presents a convex-analytic framework to learn sparse graphs from data. While our problem formulation is inspired by an extension of the graphical lasso using the so-called combinatorial graph Laplacian framework, a key differenc…