- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3(+1)
Read review
Paper summary
The paper proposes VEGA, a lightweight framework for visual-instruction image editing that directly executes in-image annotations such as boxes, arrows, text, and doodles. It trains instruction-specific LoRA experts with attention-routing supervision and selective execution, and introduces Attention Response Routing (ARR) to efficiently compose independently trained experts within a shared denoising trajectory. The authors further construct All-in-Image-45K and All-in-Image-Bench, and experiments on their benchmark and VP-Bench demonstrate improved spatial localization and visual-instruction execution over existing editors.
Critical strengths
- The paper identifies the “Reading without Routing” failure mode, offering a clear motivation for improving how pretrained editors translate visual annotations into localized editing actions.
- Attention-routing supervision is simple yet effective, with controlled ablations showing substantial improvements in execution accuracy and spatial localization.
- VEGA provides a lightweight and modular expert framework, enabling independently trained LoRA experts to be composed through ARR without joint expert training or inference-time edit masks.
Critical weaknesses
- ARR underperforms the simpler independent prediction mixing baseline on the core compositional metric (49.8% vs. 57.7% strict success), despite compositional editing being a central contribution of the paper. Although ARR improves Edit-IoU and efficiency, this result raises concerns about whether the proposed routing mechanism can reliably preserve and combine individual expert capabilities.
- The performance is highly uneven across instruction types. In particular, the Force/Arrow expert achieves only 29.7% accuracy individually and drops to 21.0% under composition, substantially below the other experts. Since directional object relocation is a fundamental visual editing operation, this weakness limits the claimed generality and composability of VEGA.
- I am concerned about the reliability of the evaluation protocol. Strict Execution relies on binary judgments from Qwen3-VL-4B, but the paper provides no human agreement study or other validation demonstrating that this relatively small VLM is a reliable judge for fine-grained spatial editing. Similarly, Outside PSNR/LPIPS is computed after an empirically fixed 16-pixel dilation without sensitivity analysis, making it unclear how robust the reported preservation advantages are to this design choice.
- Could the authors report results on VIBE [1]? Since VIBE directly targets visual-instruction-driven image editing and closely aligns with the core problem studied in this paper, it would serve as a particularly relevant external benchmark for VEGA.
[1] How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing
Questions for authors
Please refer to the weaknesses.