ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis

Dimensions overall score 7.0

• ET-SAM accelerates scene text detection and layout analysis by efficiently predicting point prompts, enabling faster inference and better data utilization. However, the typical reliance on pixel-level text segmentation for sampling thousands of foreground points as prompts leads to unsatisfied inference latency and limited data utilization.problem 35%
  Evidencepartial

  ET-SAM accelerates scene text detection and layout analysis by efficiently predicting point prompts, enabling faster inference and better data utilization. However, the typical reliance on pixel-level text segmentation for sampling thousands of foreground points as prompts leads to unsatisfied inference latency and limited data utilization.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• Previous works based on Segment Anything Model (SAM) have achieved promising performance in unified scene text detection and layout analysis. However, the typical reliance on pixel-level text segmentation for sampling thousands of foreground points as prompts leads to unsatisfied inference latency and limited data utilization.method 35%
  Evidencepartial

  Previous works based on Segment Anything Model (SAM) have achieved promising performance in unified scene text detection and layout analysis. However, the typical reliance on pixel-level text segmentation for sampling thousands of foreground points as prompts leads to unsatisfied inference latency and limited data utilization.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• ScienceToStartup currently rates this 7.0/10 on the public viability pass. For these datasets, we introduce three corresponding sets of learnable task prompts in both the point decoder and hierarchical mask decoder to mitigate discrepancies across datasets.Extensive experiments demonstrate that, compared to the previous SAM-based architecture, ET-SAM achieves about 3$\times$ inference acceleration while obtaining competitive performance on HierText, and improves an average of 11.0% F-score on Total-Text, CTW1500, and ICDAR15. Code availability is flagged in the production record; the public repository link still needs proof alignment.result 35%
  Evidencepartial

  ScienceToStartup currently rates this 7.0/10 on the public viability pass. For these datasets, we introduce three corresponding sets of learnable task prompts in both the point decoder and hierarchical mask decoder to mitigate discrepancies across datasets.Extensive experiments demonstrate that, compared to the previous SAM-based architecture, ET-SAM achieves about 3$\times$ inference acceleration while obtaining competitive performance on HierText, and improves an average of 11.0% F-score on Total-Text, CTW1500, and ICDAR15. Code availability is flagged in the production record; the public repository link still needs proof alignment.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• Scene Text Analysis moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.why now 35%
  Evidencepartial

  Scene Text Analysis moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

Competitive landscape

ET-SAM accelerates scene text detection and layout analysis by efficiently predicting point prompts, enabling faster inference and better data utilization.