Giuseppe Valenzise

World models are increasingly used to predict and simulate how environments evolve, yet their evaluation remains fragmented across video generation, autonomous driving, and robotics. World-model benchmarks differ in four respects: what capability is evaluated, how the model is evaluated, which metrics are used, and where the data come from. Thus, similar scores may reflect different evidence and do not necessarily support the same capability claims. We present an evaluation-centric survey of 102 representative benchmarks released between 2018 and 2026. We characterize them through four coupled dimensions: Evaluation Target, Evaluation Protocol, Evaluation Metrics, and Evaluation Data. Evaluation Target encompasses visual and temporal quality, spatial and state consistency, long-horizon memory and state persistence, physical plausibility, causal and counterfactual reasoning, control fidelity and interactive dynamics, and functional utility. Our analysis reveals that evaluation targets are expanding toward Control Fidelity and Interactive Dynamics and Functional Utility. However, benchmarks in the former category predominantly use open-loop protocols, leaving reliability under feedback-driven interaction insufficiently tested. These findings highlight the need to align evaluation protocols, metrics, and data with the capability claims they are intended to support. We identify priorities for evaluating functional utility across downstream roles, developing intervention-based and closed-loop protocols, combining prediction-level and downstream outcome metrics, constructing multimodal action-grounded data, and building standardized and reproducible evaluation toolkits. By clarifying what each benchmark measures and which claims its evidence can support, this survey provides a roadmap toward credible and comparable world-model evaluation. The survey website is available at https://world-model-benchmarks.github.io/.

3D Gaussian Splatting (3DGS) has recently emerged as a pioneering approach in explicit scene rendering and computer graphics. Unlike traditional neural radiance field (NeRF) methods, which typically rely on implicit, coordinate-based models to map spatial coordinates to pixel values, 3DGS utilizes millions of learnable 3D Gaussians. Its differentiable rendering technique and inherent capability for explicit scene representation and manipulation positions 3DGS as a potential game-changer for the next generation of 3D reconstruction and representation technologies. This enables 3DGS to deliver real-time rendering speeds while offering unparalleled editability levels. However, despite its advantages, 3DGS suffers from substantial memory and storage requirements, posing challenges for deployment on resource-constrained devices. In this survey, we provide a comprehensive overview focusing on the scalability and compression of 3DGS. We begin with a detailed background overview of 3DGS, followed by a structured taxonomy of existing compression methods. Additionally, we analyze and compare current methods from the topological perspective, evaluating their strengths and limitations in terms of fidelity, compression ratios, and computational efficiency. Furthermore, we explore how advancements in efficient NeRF representations can inspire future developments in 3DGS optimization. Finally, we conclude with current research challenges and highlight key directions for future exploration.

The metaverse has emerged as a transformative platform that blends physical and digital realities, supporting immersive communication, interaction, and service delivery. At the core of these experiences are avatars, digital embodiments of users, that serve as interactive interfaces across a wide range of metaverse services, including virtual collaboration, education, healthcare, entertainment, e-commerce, etc. However, the fragmented ecosystem of tools, platforms, and proprietary formats has led to significant challenges in avatar interoperability, preventing seamless user identity and experience across applications. In response, numerous international standardization bodies have launched initiatives to define interoperable and modular avatar frameworks. This survey represents the first comprehensive review of these initiatives with a focus on service-oriented requirements, revealing the concept of Avatar-as-a-Service (AaaS). It examines both historical foundations and recent advances, with a particular attention given to the emerging ISO/IEC 23090-39 standard (MPEG-I Part 39 Avatar Representation Format, ARF). By synthesizing technical approaches, standardization efforts, and open challenges, this work presents a roadmap for the evolution of AaaS and highlights emerging opportunities for delivering personalized, high-fidelity, and cross-compatible avatar experiences to support the next generation of metaverse services.

Video Quality Assessment (VQA) strives to computationally emulate human perceptual judgments and has garnered significant attention given its widespread applicability. However, existing methodologies face two primary impediments: (1) limited proficiency in evaluating samples at quality extremes (e.g., severely degraded or near-perfect videos), and (2) insufficient sensitivity to nuanced quality variations arising from a misalignment with human perceptual mechanisms. Although vision-language models offer promising semantic understanding, their reliance on visual encoders pre-trained for high-level tasks often compromises their sensitivity to low-level distortions. To surmount these challenges, we propose the Restoration-Assisted Multi-modality VQA (RAM-VQA) framework. Uniquely, our approach leverages video restoration as a proxy to explicitly model distortion-sensitive features. The framework operates through two synergistic stages: a prompt learning stage that constructs a quality-aware textual space using triple-level references (degraded, restored, and pristine) derived from the restoration process, and a dual-branch evaluation stage that integrates semantic cues with technical quality indicators via spatio-temporal differential analysis. Extensive experiments demonstrate that RAM-VQA achieves state-of-the-art performance across diverse benchmarks, exhibiting superior capability in handling extreme-quality content while ensuring robust generalization.

Recent years have witnessed increasing interest towards image aesthetics assessment (IAA), which predicts the aesthetic appeal of images by simulating human perception. The state-of-the-art IAA methods, despite their significant advancements, typically rely heavily on time-consuming and labor-intensive human annotation of aesthetic scores. Furthermore, they are subject to the generalization challenge, which is highly desired in real-world applications. Motivated by this, zero-shot image aesthetics assessment (ZIAA) is investigated to achieve robust model generalization without relying on manual aesthetic annotations, which remains largely underexplored. Specifically, a novel aesthetic prompt learning framework for ZIAA, dubbed AesPrompt, is presented in this paper. The key insight of AesPrompt is to emulate the human aesthetic perception process for learning aesthetic-oriented prompts in a multi-granularity manner. First, we first develop a new pseudo aesthetic distribution generation paradigm based on multi-LLM ensemble. Then, external knowledge of multi-granularity prompts encompassing image themes, emotions, and aesthetics is acquired. Through learning the multi-granularity aesthetic-oriented prompts, the proposed method achieves better generalization and interpretability. Extensive experiments on five IAA benchmarks demonstrate that AesPrompt consistently outperforms the state-of-the-art ZIAA methods across diverse-sourced images, covering natural images, artistic images, and artificial intelligence-generated images.

Recent years have witnessed increasing interest towards image aesthetics assessment (IAA), which predicts the aesthetic appeal of images by simulating human perception. The state-of-the-art IAA methods, despite their significant advancements, typically rely heavily on time-consuming and laborintensive human annotation of aesthetic scores. Furthermore, they are subject to the generalization challenge, which is highly desired in real-world applications. Motivated by this, zero-shot image aesthetics assessment (ZIAA) is investigated to achieve robust model generalization without relying on manual aesthetic annotations, which remains largely underexplored. Specifically, a novel aesthetic prompt learning framework for ZIAA, dubbed AesPrompt, is presented in this paper. The key insight of AesPrompt is to emulate the human aesthetic perception process for learning aesthetic-oriented prompts in a multi-granularity manner. First, we first develop a new pseudo aesthetic distribution generation paradigm based on multi-LLM ensemble. Then, external knowledge of multi-granularity prompts encompassing image themes, emotions, and aesthetics is acquired. Through learning the multi-granularity aesthetic-oriented prompts, the proposed method achieves better generalization and interpretability. Extensive experiments on five IAA benchmarks demonstrate that AesPrompt consistently outperforms the state-of-the-art ZIAA methods across diverse-sourced images, covering natural images, artistic images, and artificial intelligence-generated images. The source code is available at https://github.com/sxfly99/AesPrompt.

The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware representation and lifelike synthesis. Generative Face Video Coding (GFVC) stands at the forefront of this revolution, which could characterize complex facial dynamics into compact latent codes for bitstream compactness at the encoder side and leverages powerful deep generative models to reconstruct high-fidelity face signal from the compressed latent codes at the decoder side. As such, this well-designed GFVC paradigm could enable high-fidelity face video communication at ultra-low bitrate ranges, far surpassing the capabilities of the latest Versatile Video Coding (VVC) standard. To pioneer foundational research and accelerate the evolution of GFVC, this paper presents the first comprehensive survey of GFVC technologies, systematically bridging critical gaps between theoretical innovation and industrial standardization. In particular, we first review a broad range of existing GFVC methods with different feature representations and optimization strategies, and conduct a thorough benchmarking analysis. In addition, we construct a large-scale GFVC-compressed face video database with subjective Mean Opinion Scores (MOSs) based on human perception, aiming to identify the most appropriate quality metrics tailored to GFVC. Moreover, we summarize the GFVC standardization potentials with a unified high-level syntax and develop a low-complexity GFVC system which are both expected to push forward future practical deployments and applications. Finally, we envision the potential of GFVC in industrial applications and deliberate on the current challenges and future opportunities.

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of multimodal representations often blend semantic and perceptual elements, placing a particular emphasis on semantics. However, this could be problematic for popular tasks like image quality assessment (IQA) and conditional image generation (CIG), which typically need to have fine control on perceptual and semantic features. Motivated by the above facts, this paper presents a new multimodal disentangled representation learning framework, which leverages disentangled text to guide image disentanglement. To this end, we first build an I&2T (one Image with a perceptual Text and a semantic Text) dataset, which consists of disentangled perceptual and semantic text descriptions for an image. Then, the disentangled text descriptions are utilized as supervisory signals to disentangle pure perceptual representations from CLIP's original `coarse' feature space, dubbed DeCLIP. Finally, the decoupled feature representations are used for both image quality assessment (technical quality and aesthetic quality) and conditional image generation. Extensive experiments and comparisons have demonstrated the advantages of the proposed method on the two popular tasks. The dataset, code, and model will be available.

Point cloud data is a large collection of high dimensional 3D points with 3D coordinates and attributes, which has been one of the mainstream representations for emerging 3D applications, such as virtual reality, autonomous vehicles, and robotics. Due to the large‐scale unstructured high‐dimensional nature of point clouds, point cloud processing, transmitting and analysing has been challenging issues in multimedia signal processing and communication. Deep learning is a powerful tool to learn statistical knowledge from massive data. Advances in artificial intelligence, especially deep learning models are offering new opportunities for point cloud processing, compression and analysis. This special issue aims at promoting cutting‐edge research on deep learning‐based point cloud processing, including object detection, segmentation, registration, compression, and visual quality assessment.