2 citations · 3 across the 35 of their papers we have counts for
18 papers · 1 filter
Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models
Imad Eddine Marouf, Khalid Oublal, Enzo Tartaglione +1
Prompt learning adapts vision-language models such as CLIP by optimizing a short learnable prompt. The cross-entropy objective pulls this prompt toward base-class specialization, w…
Nix and Fix: Targeting 1000x Compression of 3D Gaussian Splatting with Diffusion Models
Cem Eteke, Enzo Tartaglione
3D Gaussian Splatting (3DGS) revolutionized novel view rendering. Instead of inferring from dense spatial points, as implicit representations do, 3DGS uses sparse Gaussians. This e…
RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting
Hoang-Nhat Tran, Francesco Di Sario, Gabriele Spadaro +2
Recent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its ef…
Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo +5
Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, re…
I-INR: Iterative Implicit Neural Representations
Ali Haider, Muhammad Salman Ali, Maryam Qamar +5
Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural…
Lightweight Embedded FPGA Deployment of Learned Image Compression with Knowledge Distillation and Hybrid Quantization
Alaa Mazouz, Sumanta Chaudhuri, Marco Cagnanzzo +3
Learnable Image Compression (LIC) has shown the potential to outperform standardized video codecs in RD efficiency, prompting the research for hardware-friendly implementations. Mo…
Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering
Imad Eddine Marouf, Enzo Tartaglione, Stephane Lathuiliere +1
Continual Learning in Visual Question Answering (VQACL) requires models to acquire new visual-linguistic skills (plasticity) while preserving previously learned knowledge (stabilit…
GoDe: Gaussians on Demand for Backbone-Agnostic Progressive Compression
Francesco Di Sario, Riccardo Renzulli, Marco Grangetto +2
Splat-based radiance fields have rapidly diversified in primitive type, kernel support, and appearance parameterization. This diversity makes compression difficult: most codecs are…
FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance
Haicheng Wang, Zhemeng Yu, Gabriele Spadaro +4
Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. Ho…
Efficient Progressive Image Compression with Variance-aware Masking
Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti +2
Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compre…
ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting
Muhammad Salman Ali, Sung-Ho Bae, Enzo Tartaglione
3D models have recently been popularized by the potentiality of end-to-end training offered first by Neural Radiance Fields and most recently by 3D Gaussian Splatting models. The l…
STanH : Parametric Quantization for Variable Rate Learned Image Compression
Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti +1
In end-to-end learned image compression, encoder and decoder are jointly trained to minimize a cost function, where controls the trade-off between rate of the quantize…
WiGNet: Windowed Vision Graph Neural Network
Gabriele Spadaro, Marco Grangetto, Attilio Fiandrotti +2
In recent years, Graph Neural Networks (GNNs) have demonstrated strong adaptability to various real-world challenges, with architectures such as Vision GNN (ViG) achieving state-of…
Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning
Muhammad Salman Ali, Maryam Qamar, Sung-Ho Bae +1
In recent times, the utilization of 3D models has gained traction, owing to the capacity for end-to-end training initially offered by Neural Radiance Fields and more recently by 3D…
Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering
Francesco Di Sario, Riccardo Renzulli, Enzo Tartaglione +1
Since the introduction of NeRFs, considerable attention has been focused on improving their training and inference times, leading to the development of Fast-NeRFs models. Despite d…
Domain Adaptation for Learned Image Compression with Supervised Adapters
Alberto Presta, Gabriele Spadaro, Enzo Tartaglione +2
In Learned Image Compression (LIC), a model is trained at encoding and decoding images sampled from a source domain, often outperforming traditional codecs on natural images; yet i…
Mini but Mighty: Finetuning ViTs with Mini Adapters
Imad Eddine Marouf, Enzo Tartaglione, Stéphane Lathuilière
Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning. Recent wo…
Enhancing Plasticity for First Session Adaptation Continual Learning
Imad Eddine Marouf, Subhankar Roy, Stéphane Lathuilière +1
The integration of large pre-trained models (PTMs) into Class-Incremental Learning (CIL) has facilitated the development of computationally efficient strategies such as First-Sessi…