Related papers: VEFX-Bench: A Holistic Benchmark for Generic Video…
Reliable procedural monitoring in video requires exposure to naturally occurring human errors and the recoveries that follow. In egocentric recordings, mistakes are often partially occluded by hands and revealed through subtle object state…
The rapid advancement in AI-generated video synthesis has led to a growth demand for standardized and effective evaluation metrics. Existing metrics lack a unified framework for systematically categorizing methodologies, limiting a holistic…
Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the infrastructure for S2V generation, we propose OpenS2V-Nexus,…
Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess…
We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of ~3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality…
Video-to-audio generation (V2A) is of increasing importance in domains such as film post-production, AR/VR, and sound design, particularly for the creation of Foley sound effects synchronized with on-screen actions. Foley requires…
Human-generated reward signals are critical for aligning generative models with human preferences, guiding both training and inference-time evaluations. While large language models (LLMs) employed as proxy evaluators, i.e., LLM-as-a-Judge,…
Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics. We introduce…
We introduce MotionEdit, a novel dataset for motion-centric image editing-the task of modifying subject actions and interactions while preserving identity, structure, and physical plausibility. Unlike existing image editing datasets that…
While there is overall agreement that future technology for organizing, browsing and searching videos hinges on the development of methods for high-level semantic understanding of video, so far no consensus has been reached on the best way…
Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from…
We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal…
Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…
Quality assessment of videos is crucial for many computer graphics applications, including video games, virtual reality, and augmented reality, where visual performance has a significant impact on user experience. When test videos cannot be…
The recent developments in Large Multi-modal Video Models (Video-LMMs) have significantly enhanced our ability to interpret and analyze video data. Despite their impressive capabilities, current Video-LMMs have not been evaluated for…
The rapid advancement of video generation models has made it increasingly challenging to distinguish AI-generated videos from real ones. This issue underscores the urgent need for effective AI-generated video detectors to prevent the…
Face video quality assessment (FVQA) deserves to be explored in addition to general video quality assessment (VQA), as face videos are the primary content on social media platforms and human visual system (HVS) is particularly sensitive to…
While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend…
Image editing models are advancing rapidly, yet comprehensive evaluation remains a significant challenge. Existing image editing benchmarks generally suffer from limited task scopes, insufficient evaluation dimensions, and heavy reliance on…
The generative capabilities of Large Language Models (LLMs) are rapidly expanding from static code to dynamic, interactive visual artifacts. This progress is bottlenecked by a critical evaluation gap: established benchmarks focus on…