16 citations · 24 across the 28 of their papers we have counts for
32 papers
Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates
Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega
Block-based video codecs select coding parameters based on the input by optimizing a rate-distortion trade-off. The conventional distortion choice, the sum of squared errors (SSE),…
Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms
Samuel Fernández-Menduiña, Amir Ziashahabi, Eduardo Pavez +2
Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is bandwidth-bound. Hence, reducing…
Motion Estimation Techniques for Volumetric Video Attribute Compression
Haoran Hong, Eduardo Pavez, Antonio Ortega +2
Point cloud compression relies on techniques to compress both geometry and attributes. Motion-based approaches for dynamic solid point cloud geometry compression within the geometr…
GS-NFS: Bandwidth-adaptive Streaming of Dynamic Gaussian Splats and Point Clouds
Rajrup Ghosh, Haodong Wang, Haoran Hong +6
Dynamic 3D Gaussian Splatting (3DGS) holds great promise as a 3D video streaming technology since it can represent complex 3D scenes with high fidelity. In this approach, every fra…
FaSST: Fast Sparsifying Secondary Transform
Darukeesan Pakiyarajah, Samuel Fernández-Menduiña, Eduardo Pavez +2
Data-dependent secondary transforms, which aim to decorrelate coefficients of a separable primary transform, can improve residual coding efficiency; however, their deployment is of…
Rate-Distortion Optimization for Ensembles of Non-Reference Metrics
Xin Xiong, Samuel Fernández-Menduiña, Eduardo Pavez +3
Non-reference metrics (NRMs) can assess the visual quality of images and videos without a reference, making them well-suited for the evaluation of user-generated content. Nonethele…
L2G-Net: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations
Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega
Despite their theoretical advantages, spectral methods based on the graph Fourier transform (GFT) are seldom used in graph neural networks (GNNs) due to the cost of computing the e…
Wrapper-Aware Rate-Distortion Optimization in Feature Coding for Machines
Samuel Fernández-Menduiña, Hyomin Choi, Fabien Racapé +2
Feature coding for machines (FCM) is a lossy compression paradigm for split-inference. The transmitter encodes the outputs of the first part of a neural network before sending them…
Avoiding Quality Saturation in UGC Compression Using Denoised References
Xin Xiong, Samuel Fernández-Menduiña, Eduardo Pavez +3
Video-sharing platforms must re-encode large volumes of noisy user-generated content (UGC) to meet streaming demands. However, conventional codecs, which aim to minimize the mean s…
Region-Adaptive Learned Hierarchical Encoding for 3D Gaussian Splatting Data
Shashank N. Sridhara, Birendra Kathariya, Fangjun Pu +3
We introduce Region-Adaptive Learned Hierarchical Encoding (RALHE) for 3D Gaussian Splatting (3DGS) data. While 3DGS has recently become popular for novel view synthesis, the size…
Adaptive Voxelization for Transform coding of 3D Gaussian splatting data
Chenjunjie Wang, Shashank N. Sridhara, Eduardo Pavez +2
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 3DG…
Joint Optimization of Primary and Secondary Transforms Using Rate-Distortion Optimized Transform Design
Darukeesan Pakiyarajah, Eduardo Pavez, Antonio Ortega +4
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),…
Rate-Distortion Optimization with Non-Reference Metrics for UGC Compression
Samuel Fernández-Menduiña, Xin Xiong, Eduardo Pavez +3
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 challen…
Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization
Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega
Many images and videos are primarily processed by computer vision algorithms, involving only occasional human inspection. When this content requires compression before processing,…
Towards joint graph learning and sampling set selection from data
Shashank N. Sridhara, Eduardo Pavez, Antonio Ortega
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…
Color-Guided Flying Pixel Correction in Depth Images
Ekamresh Vasudevan, Shashank N. Sridhara, Eduardo Pavez +3
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 backgrou…
Graph-based Scalable Sampling of 3D Point Cloud Attributes
Shashank N. Sridhara, Eduardo Pavez, Ajinkya Jayawant +3
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 computational…
Graph-Based Signal Sampling with Adaptive Subspace Reconstruction for Spatially-Irregular Sensor Data
Darukeesan Pakiyarajah, Eduardo Pavez, Antonio Ortega
Choosing an appropriate frequency definition and norm is critical in graph signal sampling and reconstruction. Most previous works define frequencies based on the spectral properti…
Fast DCT+: A Family of Fast Transforms Based on Rank-One Updates of the Path Graph
Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega
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-use…
Feature-Preserving Rate-Distortion Optimization in Image Coding for Machines
Samuel Fernández Menduiña, Eduardo Pavez, Antonio Ortega
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 down…
Full reference point cloud quality assessment using support vector regression
Ryosuke Watanabe, Shashank N. Sridhara, Haoran Hong +4
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 compr…
Full-reference Point Cloud Quality Assessment Using Spectral Graph Wavelets
Ryosuke Watanabe, Keisuke Nonaka, Eduardo Pavez +2
Point clouds in 3D applications frequently experience quality degradation during processing, e.g., scanning and compression. Reliable point cloud quality assessment (PCQA) is impor…
Irregularity-Aware Bandlimited Approximation for Graph Signal Interpolation
Darukeesan Pakiyarajah, Eduardo Pavez, Antonio Ortega
In most work to date, graph signal sampling and reconstruction algorithms are intrinsically tied to graph properties, assuming bandlimitedness and optimal sampling set choices. How…
Fast graph-based denoising for point cloud color information
Ryosuke Watanabe, Keisuke Nonaka, Eduardo Pavez +2
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, re…