A 1,000-pair real-world HDR benchmark with two new affine-invariant error scores shows the best image-editing models reproduce the relative structure of real light transport but degrade in dim regions, and that VLMs fail at pixel-level light checks.
Commonsense-t2i challenge: Can text-to-image generation models understand commonsense?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5representative citing papers
T2I-FactualBench is a new three-tier benchmark for factuality of knowledge-intensive concepts in T2I models, using multi-round VQA evaluation to show SOTA models need improvement.
IR-guided diffusion injects intermediate text representations into early denoising steps to improve alignment for one-and-only objects, reporting up to 19.1pp VQAScore gains on OAO-AttackBench and other benchmarks.
PhyGenBench supplies 160 prompts across 27 physical laws and an automated LLM/VLM evaluation pipeline to measure physical commonsense compliance in current text-to-video models.
citing papers explorer
-
Do Image Editing Models Understand Lighting?
A 1,000-pair real-world HDR benchmark with two new affine-invariant error scores shows the best image-editing models reproduce the relative structure of real light transport but degrade in dim regions, and that VLMs fail at pixel-level light checks.
-
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
T2I-FactualBench is a new three-tier benchmark for factuality of knowledge-intensive concepts in T2I models, using multi-round VQA evaluation to show SOTA models need improvement.
-
Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment
IR-guided diffusion injects intermediate text representations into early denoising steps to improve alignment for one-and-only objects, reporting up to 19.1pp VQAScore gains on OAO-AttackBench and other benchmarks.
-
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
PhyGenBench supplies 160 prompts across 27 physical laws and an automated LLM/VLM evaluation pipeline to measure physical commonsense compliance in current text-to-video models.
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation