Related papers: Physion-Eval: Evaluating Physical Realism in Gener…
We investigate how to enhance the physical fidelity of video generation models by leveraging synthetic videos derived from computer graphics pipelines. These rendered videos respect real-world physics, such as maintaining 3D consistency,…
Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent results, particularly when handling large-scale or complex…
While video large language models (Video-LLMs) excel in understanding slow-paced, real-world egocentric videos, their capabilities in high-velocity, information-dense virtual environments remain under-explored. Existing benchmarks focus on…
High-quality benchmarks are crucial for driving progress in machine learning research. However, despite the growing interest in video generation, there is no comprehensive dataset to evaluate human generation. Humans can perform a wide…
Thanks to recent advancements in scalable deep architectures and large-scale pretraining, text-to-video generation has achieved unprecedented capabilities in producing high-fidelity, instruction-following content across a wide range of…
Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models. The various inconsistencies and defects observed in such videos…
Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and…
Physically Plausible Video Generation (PPVG) has emerged as a promising avenue for modeling real-world physical phenomena. PPVG requires an understanding of commonsense knowledge, which remains a challenge for video diffusion models.…
Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied…
Over the years, performance evaluation has become essential in computer vision, enabling tangible progress in many sub-fields. While talking-head video generation has become an emerging research topic, existing evaluations on this topic…
Large-scale video generation models have demonstrated emergent physical coherence, positioning them as potential world models. However, a gap remains between contemporary "stateless" video architectures and classic state-centric world model…
With AI-generated videos increasingly indistinguishable from reality, current benchmarks primarily focus on broad semantic alignment and basic physical consistency, offering limited discriminative power for evaluating them. To address this,…
Recognizing pain in video is crucial for improving patient-computer interaction systems, yet traditional data collection in this domain raises significant ethical and logistical challenges. This study introduces a novel approach that…
Realistic object interactions are crucial for creating immersive virtual experiences, yet synthesizing realistic 3D object dynamics in response to novel interactions remains a significant challenge. Unlike unconditional or text-conditioned…
Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation pipelines rely heavily on human…
Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered…
Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. However, state-of-the-art video diffusion models frequently produce implausible results such as…
Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time…
Generative AI (GenAI) models have revolutionized animation, enabling the synthesis of humans and motion patterns with remarkable visual fidelity. However, generating truly realistic human animation remains a formidable challenge, where even…
Evaluating the quality of videos generated from text-to-video (T2V) models is important if they are to produce plausible outputs that convince a viewer of their authenticity. We examine some of the metrics used in this area and highlight…