- Rating
- 4
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper focuses on 3D scene reconstruction via an image-to-code approach. The approach iteratively writes and improves the program by rendering out the blender code the agent writes. The authors propose a benchmark, LEGO-Bench which enables evaluation of their method and similar baselines. The propose LEGO-Plugin, a harness that improves various LLMs in this task. They evaluate in settings comparable to classical reconstruction via LEGO-World. The authors present findings based on the results.
Critical strengths
- The authors study the problem comprehensively and shares findings such as the effect of reasoning on different model tiers, these findings are useful to the community.
- The harness design includes analysis, such as judgement correctness evaluation. This makes the design motivated rather than purely trial-and-error.
- The authors make image-to-code comparable with classical reconstruction methods on known datasets, and highlight their current limitations, which motivates future development.
Critical weaknesses
I like the paper and the results. The main weakness I find is about the wording of the contribution, which slightly over-claims.
- In terms of contribution wording of "LEGO-Anything framework"- the iterative code writing+review loop is quite common, and I do not consider LEGO-Anything a different framing from any existing agentic work. I do appreciate the method, and it might be better to just say this paper shares analysis and LEGO-Plugin, a harness
- Naming LEGO-World as an evaluation setting contribution. I really appreciate the LEGO-World evaluation and feel it's important to put this on the same datasets as traditional methods. Maybe just say you make it comparable to vision methods, rather than setting it up as a new setting with a new name.
Questions for authors
- Could you compare with AHA3D (https://kevinxu02.github.io/real2sim-indoor-site/), which is a similar blender scene generation harness?
- Would appreciate toning down the novelty claim on framework and evaluation setting. The paper provides clear and informative analysis and a useful harness, which in my opinion is sufficient contributions, and the additional contribution claiming feels untrue and overdone.
4 comments
Response to R1 Hyx8 (1/1)
[Weaknesses 1 & 2, Question 2 - Toning Down Contribution Wording]
“I like the paper and the results. The main weakness I find is about the wording of the contribution, which slightly over-claims.
- In terms of contribution wording of "LEGO-Anything framework"- the iterative code writing+review loop is quite common, and I do not consider LEGO-Anything a different framing from any existing agentic work. I do appreciate the method, and it might be better to just say this paper shares analysis and LEGO-Plugin, a harness
- Naming LEGO-World as an evaluation setting contribution. I really appreciate the LEGO-World evaluation and feel it's important to put this on the same datasets as traditional methods. Maybe just say you make it comparable to vision methods, rather than setting it up as a new setting with a new name.”
“Would appreciate toning down the novelty claim on framework and evaluation setting. The paper provides clear and informative analysis and a useful harness, which in my opinion is sufficient contributions, and the additional contribution claiming feels untrue and overdone.”
[Response]
We agree and have revised the Abstract, Introduction, Section 3, and Section 6 to remove any over-claiming:
- Reframing LEGO-Anything: Rather than claiming the iterative code–render–inspect loop as a novel framework, we now present it strictly as our problem formulation and study testbed, centering our core contributions on LEGO-Bench, our empirical trajectory diagnostics, and the LEGO-Plugin harness.
- De-branding LEGO-World: Following your suggestion, we no longer frame LEGO-World as a newly named evaluation setting contribution. Instead, Section 6 is presented directly as a downstream vision readout analysis that makes reconstructed scenes directly comparable to classical perception models on standard benchmarks (COCO, LVIS, and ETH3D).
[Question 1 - Comparison with AHA3D]
“Could you compare with AHA3D (https://kevinxu02.github.io/real2sim-indoor-site/), which is a similar blender scene generation harness?”
[Response]
Thank you for pointing us to AHA3D! AHA3D is a concurrent study. To provide our readers a better understanding of the field, we have cited and discussed AHA3D in Appendix A.4 and added a direct comparison between our proposed LEGO-Plugin in Appendix B.7.
Table 1. Comparison between LEGO-Plugin and AHA3D on an indoor subset (%).
| Model | Settings | Validity | Reconstruction | Appearance | Final Score |
|---|---|---|---|---|---|
| GPT-5.6-Sol | Vanilla | 100.00 | 16.28 | 14.91 | 15.59 |
| with AHA3D | 100.00 | 16.51 | 20.46 | 18.49 | |
| with LEGO Plugin | 100.00 | 34.27 | 35.99 | 35.13 | |
| GPT-6-Sol | Vanilla | 100.00 | 22.93 | 42.27 | 32.60 |
| with AHA3D | 100.00 | 27.18 | 35.82 | 31.50 | |
| with LEGO Plugin | 100.00 | 34.42 | 39.31 | 36.86 |
Thank you! I will maintain my score.
We are glad to see we could improve the quality of the manuscript with your review. Thanks for your time and efforts!
Response to R1 Hyx8
We sincerely thank you for recognizing our comprehensive empirical findings, LEGO-Plugin harness design and evaluation settings with classical CV methods! We hope the following responses address your feedbacks. Please let us know If you have any further inquiries!