TextSculptor supplies an automated data synthesis pipeline yielding 3.2M samples plus a four-task benchmark that raises open-source scene text editing performance.
Densefusion-1m: Merging vision experts for comprehensive multimodal perception.Advances in Neural Information Processing Systems, 37:18535–18556, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TextSculptor: Training and Benchmarking Scene Text Editing
TextSculptor supplies an automated data synthesis pipeline yielding 3.2M samples plus a four-task benchmark that raises open-source scene text editing performance.