- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes Dovetail3D, which post-trains a single VLM (Qwen3.5-9B) to build 3D indoor scenes by retrieving, selecting and placing assets one at a time. A hand-written rule compiler prunes the coordinate space into feasible regions, and the agent picks the final placement inside them. Training uses GRPO with hierarchical credit: feasibility-based layout credits, and an LLM-judge style score distributed to individual assets. On 3D-FRONT, it reports zero out-of-bounds and collisions, higher relation scores, and small gains in judged style, compared with seven baselines.
Critical strengths
- Well-motivated design: Exposing state-dependent feasible regions as the action space, while leaving the final choice to the policy, is a sensible middle ground between tool-based reliability and model-driven flexibility.
- Useful learning signal: The feasible-domain return rewards placements that keep space open for later assets. This is a new and intuitive way to give credit for long-horizon layout decisions.
- Strong layout results and transparency: The method reaches zero out-of-bounds and collisions with clear gains in relation metrics. The appendix gives detailed rules, rubrics and hyperparameters, and code is provided.
Critical weaknesses
- Evaluation overlaps with the method: The pruning rules likely resemble the rule-based OOR/OAR/ACN metrics, and OOB = COL = 0 holds by construction. CNT also trails ReSpace in some rooms (e.g., 88.4 vs. 99.8 in living rooms) without discussion.
- Ablations are incomplete: There is no ablation of the pruning itself, and Table 3 is a single run on one room type.
Questions for authors
I would like the authors to address the three weaknesses above.
3 comments
Thank you for the authors' responses. The additional experiments have addressed most of my concerns. I have no further questions. I hope these experiments can be included in the final version of the paper. I will keep my current score.
We sincerely thank the reviewer for the encouraging feedback and for acknowledging our responses. We will carefully consolidate all reviewers' suggestions along with these additional experiments to update our manuscript toward the end of the rebuttal period.
Response to Reviewer WEp3
We sincerely thank the reviewer for your recognition of our work and address each concern directly below.
W1: Evaluation overlaps with the method
We first clarify that pruning enforces
OOBandCOLand overlaps only partially with the local rules assessed byOORandOARthrough LLM prompting. It does not encodeACN, which evaluates global activity-centric connectivity.LayoutVLM,I-Design,Holodeck, andSceneWeaverlikewise use solvers or optimizers and report related validity metrics.OOBandCOLare system-level guarantees, not learned-policy gains. We agree thatOOB = COL = 0for committed scenes is guaranteed by the local harness. However, the policy can still propose invalid actions before the check gate, and RL reduces this invalid-placement rate (PIR) from 16.2% to 0.3%, demonstrating learned compliance with the feasible domains.OOBandCOLare successfully bounded at zero by construction,Dovetail3Dfurther translates these structural guarantees into superior compositional quality across all room types (outperforming the strongest baseline by 0.4–0.7 points in Style and 0.2–0.7 points in overall quality).ReSpaceachieves higher Living RoomCNT(99.8% vs. 88.4%) because it forces objects into rooms without strict clearance or relational validity—resulting in a massive drop inACN(44.0% vs. 74.6%) andOOR/OAR(40.6%/88.2% vs. 86.4%/100.0%), alongside non-zero collisions (COL15.1%) and out-of-bounds (OOB1.0%).Dovetail3Dprioritizes joint layout validity and usability rather than maximizing raw object count via invalid placements.W2: Incomplete Ablations
Base w/o compiler,Base (w/o RL),Heuristic, andDovetail3D) across 200 test rooms spanning three room types. Disabling the compiler in the Base model reducesACNfrom 81.6% to 41.4% andOOR/OARfrom 90.4%/97.9% to 25.9%/23.8%, while adding RL on top of the fixed compiler (Dovetail3Dvs.Base (w/o RL)) boostsCNTby +7.0% (84.8% → 91.8%).