Image Tiling for High-Resolution Reasoning: Balancing Local Detail with Global Context
This is an incremental reproduction study that provides practical insights for researchers working on high-resolution multimodal models.
The authors reproduced and analyzed the Monkey Vision-Language Model's image tiling approach for high-resolution image understanding, confirming that tiling recovers local details but finding that results vary with task type and tile granularity.
Reproducibility remains a cornerstone of scientific progress, yet complex multimodal models often lack transparent implementation details and accessible training infrastructure. In this work, we present a detailed reproduction and critical analysis of the Monkey Vision-Language Model (VLM) (Li et al. 2023b) published in CVPR24, a recent approach to high-resolution image understanding via image tiling. The original paper proposed splitting large images into tiles to recover fine-grained visual details while maintaining computational efficiency. Our study replicates this strategy using open checkpoints and reimplements the training pipeline. We confirm the key finding of the original Monkey VLM work, namely that tiling effectively recovers local details. We then extend this work further, by investigating the effect of the inclusion of the global context, which provide practical insights for future high-resolution multimodal modeling. However, we also report deviations in the results, with the magnitude of these effects depending heavily on task type and tile granularity.