ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies
This addresses the challenge of handling intricate, interdependent instructions in image editing for AI and computer vision researchers, representing an incremental advancement in benchmarking and method improvement.
The paper tackles the problem of text-driven image editing for complex, multi-step instructions, where current models struggle, by introducing ComplexBench-Edit, a benchmark that systematically assesses performance on such tasks, and a Chain-of-Thought-based method that significantly enhances model capabilities.
Text-driven image editing has achieved remarkable success in following single instructions. However, real-world scenarios often involve complex, multi-step instructions, particularly ``chain'' instructions where operations are interdependent. Current models struggle with these intricate directives, and existing benchmarks inadequately evaluate such capabilities. Specifically, they often overlook multi-instruction and chain-instruction complexities, and common consistency metrics are flawed. To address this, we introduce ComplexBench-Edit, a novel benchmark designed to systematically assess model performance on complex, multi-instruction, and chain-dependent image editing tasks. ComplexBench-Edit also features a new vision consistency evaluation method that accurately assesses non-modified regions by excluding edited areas. Furthermore, we propose a simple yet powerful Chain-of-Thought (CoT)-based approach that significantly enhances the ability of existing models to follow complex instructions. Our extensive experiments demonstrate ComplexBench-Edit's efficacy in differentiating model capabilities and highlight the superior performance of our CoT-based method in handling complex edits. The data and code are released at https://github.com/llllly26/ComplexBench-Edit.