How Do Inpainting Artifacts Propagate to Language?
This provides a diagnostic framework for understanding visual-language interactions in multimodal systems, but it is incremental as it focuses on analyzing existing methods rather than introducing new ones.
The paper tackled the problem of how visual artifacts from diffusion-based inpainting affect language generation in vision-language models, finding consistent associations between reconstruction fidelity and caption quality across multiple datasets.
We study how visual artifacts introduced by diffusion-based inpainting affect language generation in vision-language models. We use a two-stage diagnostic setup in which masked image regions are reconstructed and then provided to captioning models, enabling controlled comparisons between captions generated from original and reconstructed inputs. Across multiple datasets, we analyze the relationship between reconstruction fidelity and downstream caption quality. We observe consistent associations between pixel-level and perceptual reconstruction metrics and both lexical and semantic captioning performance. Additional analysis of intermediate visual representations and attention patterns shows that inpainting artifacts lead to systematic, layer-dependent changes in model behavior. Together, these results provide a practical diagnostic framework for examining how visual reconstruction quality influences language generation in multimodal systems.