ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
This work addresses the problem of automated infographic generation from tables for users needing data visualization, representing an incremental advancement in multimodal reasoning and generation.
The authors tackled the challenge of generating creative table visualizations by introducing ShowTable, a pipeline that combines multimodal large language models with diffusion models through a self-correcting process, resulting in significant performance improvements over baselines on the new TableVisBench benchmark.
While existing generation and unified models excel at general image generation, they struggle with tasks requiring deep reasoning, planning, and precise data-to-visual mapping abilities beyond general scenarios. To push beyond the existing limitations, we introduce a new and challenging task: creative table visualization, requiring the model to generate an infographic that faithfully and aesthetically visualizes the data from a given table. To address this challenge, we propose ShowTable, a pipeline that synergizes MLLMs with diffusion models via a progressive self-correcting process. The MLLM acts as the central orchestrator for reasoning the visual plan and judging visual errors to provide refined instructions, the diffusion execute the commands from MLLM, achieving high-fidelity results. To support this task and our pipeline, we introduce three automated data construction pipelines for training different modules. Furthermore, we introduce TableVisBench, a new benchmark with 800 challenging instances across 5 evaluation dimensions, to assess performance on this task. Experiments demonstrate that our pipeline, instantiated with different models, significantly outperforms baselines, highlighting its effective multi-modal reasoning, generation, and error correction capabilities.