TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2503. 07265v4 Announce Type: replace-cross Abstract: Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content.
WorldGenBench is a benchmark that tests text‑to‑image models on their ability to combine factual grounding with contextual reasoning. It introduces the Knowledge Checklist Score to evaluate whether generated images reflect both explicit and implicit semantic elements. The study finds that while some proprietary models perform well, most open‑source systems struggle, especially with culturally diverse and scientific content, revealing common failure modes such as semantic hallucination and underrepresentation of non‑Western knowledge.
arXiv:2607. 15216v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs.
arXiv:2606. 10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood.
The paper introduces the Semantic Drift Protocol (SDP), a Telephone Game-inspired method to evaluate how well unified models preserve meaning when alternating between image-to-text (I2T) and text-to-image (T2I) generation over multiple generations. It defines Mean Cumulative Drift (MCD) and Multi-Generation GenEval (MGG) as metrics for semantic retention, and presents a new benchmark of 400 image‑text pairs from NoCaps and DOCCI to stress-test models beyond COCO. Applying SDP to seven models shows that models with strong single‑pass scores can still suffer severe semantic drift, revealing catastrophic failure modes that isolated benchmarks miss.
arXiv:2601. 22725v4 Announce Type: replace-cross Abstract: Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck.