Vision-language models can spot obvious virtual objects in AR photos but frequently miss seamlessly integrated ones, with performance dropping sharply as scene complexity increases.
Gemini: A family of highly capable multimodal models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble
Vision-language models can spot obvious virtual objects in AR photos but frequently miss seamlessly integrated ones, with performance dropping sharply as scene complexity increases.