- Rating
- 3
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
LivingFlow optimizes existing 3D foreground furniture rooms to improve the circulation layout of movement/navigation-oriented interior scenes. An initial scene layout is generated using LLM, followed by optimization through editing operations such as asset positioning and scaling. A trainable Qwen3.8-27B editor queries registered assets and then edits or freezes optimized assets for candidates requiring movement, rotation, and resizing. After each edit, the geometry executor re-evaluates the effectiveness of reachability and path constraints. To efficiently solve the problem, this paper combines the GiGPO adaptive algorithm with a well-designed reward rule to optimize the model's layout adjustment capabilities.
Critical strengths
The paper develops a framework called LIVINGFLOW, which introduces a furniture layout optimization framework that senses pedestrian flow. By incorporating geometric feedback based on activity context, it improves existing layouts, thus addressing to some extent a problem in the layout design field regarding how scenes can support downstream tasks. The article is clearly structured, and the charts provide strong visual support.
Critical weaknesses
-
LivingFlow can resize furniture, but the paper doesn't explicitly state whether LayoutVLM and other baseline methods can change object dimensions. If some input layouts can only be fixed by resizing, then baseline methods limited to movement and rotation might not solve these problems. Therefore, some performance gaps may stem from additional operations rather than the proposed methods themselves.
-
The paper mentions that the 2D layout is fixed, and paths are recalculated after each edit. Recalculating paths doesn't necessarily change the required passage width. Is there a minimum width, or does it depend on the embodied or user common sense? This is crucial for clarifying that the optimization goal is to achieve functional circulation, not just a passable path.
-
The paper showcases living rooms, living-dining rooms, and bedrooms, but it doesn't extend or discuss other indoor scenarios that require more circulation distribution, such as kitchens. This raises some concerns about the method's scalability.
Questions for authors
-
Compared with previous reachability optimization methods, such as PhyScene [1] and RoomPlanner [2], and agent-based approaches like SAGE [3], this work integrates these ideas into a unified framework and introduces RL-based optimization. It would be helpful if the authors could further clarify the key technical contributions and explain how the proposed approach advances beyond the combination of existing methods.
-
Is the required circulation width fixed across different scenarios, or does it vary depending on the activity and user? What factors determine whether a route is considered acceptable? It would be helpful to clarify how the proposed criteria capture the convenience and comfort of movement rather than simply ensuring that a valid path exists.
[1]:physcene:PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI [2]:RoomPlanner: Reachability-Aware View Sampling for Text-to-Room 3D Gaussian Splatting [3]:SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
2 comments
Official Response to Reviewer YteJ (2/2)
Weakness 3: Limited evidence of generalization to kitchens
Response. We added a transfer experiment on 47 kitchens and 114 bathrooms from HSSD (Section 4.4, Table 3). We applied the same 3D-FRONT LivingFlow policy to both room types without further training. All baselines were adapted to the same editing task, with nine fine-tuned on HSSD. LivingFlow leads on MPR, SR, and Valid in both room types. Relative to the input, MPR improves by 8.04 percentage points in kitchens and 7.23 in bathrooms. Bathroom SR also rises from 12.28% to 25.44%.
All values are percentages.
| Method | Kitchen MPR | Kitchen SR | Kitchen Valid | Bathroom MPR | Bathroom SR | Bathroom Valid |
|---|---|---|---|---|---|---|
| Input layout | 31.57 | 2.13 | 2.13 | 56.20 | 12.28 | 27.19 |
| DiffuScene | 16.27 | 2.13 | 2.13 | 40.88 | 6.14 | 17.54 |
| LEGO-Net | 20.94 | 2.13 | 2.13 | 47.13 | 7.89 | 18.42 |
| InstructScene | 11.94 | 2.13 | 2.13 | 36.49 | 7.02 | 20.18 |
| LayoutVLM | 4.14 | 0.00 | 0.00 | 1.94 | 0.00 | 4.39 |
| SceneReVis | 28.79 | 2.13 | 2.13 | 45.47 | 9.65 | 22.81 |
| ReSpace | 12.91 | 0.00 | 0.00 | 14.39 | 0.88 | 0.88 |
| RoomPlanner | 19.03 | 2.13 | 4.26 | 36.71 | 13.16 | 35.09 |
| SAGE | 29.89 | 2.13 | 4.26 | 38.34 | 7.89 | 28.07 |
| PhyScene | 13.28 | 2.13 | 2.13 | 40.14 | 6.14 | 16.67 |
| OID-PPO | 22.95 | 2.13 | 2.13 | 28.10 | 3.51 | 14.04 |
| HAISOR | 29.61 | 2.13 | 2.13 | 50.44 | 11.40 | 25.44 |
| iARCS | 16.04 | 2.13 | 2.13 | 41.44 | 6.73 | 16.08 |
| LivingFlow | 39.61 | 4.26 | 10.64 | 63.43 | 25.44 | 44.74 |
Question 1: Technical contribution beyond existing reachability and agent-based methods
Response. LivingFlow refines existing furnished layouts by turning transitions between consecutive furniture uses in activity chains into fixed movement tasks and recomputing access and routes after each edit to guide the next decision (Sections 3.1–3.3). Our GiGPO adaptation assigns credit over a complete tool cycle that groups the editor's queries with the resulting edit or stop decision (Section 3.5). Table 2 compares editing strategies under the shared executor.
Activity ablation. We added the w/o Activity comparison in Table 2, using the same return rule as LivingFlow. The ablated editor sees geometric feedback during editing. The fixed evaluation movements are used to rank its saved layouts after editing. In living rooms, w/o Activity reaches 85.71% Valid and 37.71% MPR, compared with 83.67% Valid and 60.33% MPR for LivingFlow. Geometrically valid layouts can still leave required movements infeasible.
| 3D-FRONT room type | LivingFlow MPR / SR / Valid (%) | w/o Activity MPR / SR / Valid (%) |
|---|---|---|
| Living room | 60.33 / 16.33 / 83.67 | 37.71 / 4.08 / 85.71 |
| Living–dining room | 74.73 / 24.00 / 92.00 | 51.37 / 8.00 / 90.00 |
| Bedroom | 74.14 / 41.76 / 97.80 | 43.13 / 19.78 / 85.71 |
Official Response to Reviewer YteJ (1/2)
Thank you for asking us to clarify the editing permissions and passage-width criterion, and for suggesting that we evaluate LivingFlow in kitchens.
Weakness 1: Potential advantage from different resizing permissions
Response. We added an audit of LayoutVLM’s edit permissions (Appendix D.2). LayoutVLM optimizes translation and yaw, and all 1,510 audited items retain their original dimensions. RoomPlanner, SAGE, PhyScene, OID-PPO, and HAISOR also use fixed furniture sizes in our evaluations.
With furniture dimensions fixed, the main-table LivingFlow checkpoint reaches 53.76% MPR and LayoutVLM reaches 37.01%, a difference of 16.75 percentage points. We applied the same ranking rule to each method’s available layouts, including the input. LayoutVLM contributes its returned layout, and LivingFlow contributes the states saved during editing. The two methods also have different permissions for other edits. The shared-executor searches in Table 2 use the same move, rotate, and resize operations as LivingFlow.
Table 2 also reports the fixed-size policy trained and evaluated without Resize, with layouts ranked by the same rule as LivingFlow.
Weakness 2 & Question 2: Fixed passage width and its relation to comfort
Response. We recalculate routes after each edit using the same 60 cm clearance threshold across activities and rooms. A movement passes when the required furniture access locations can be selected normally and a route connects them at the specified clearance (Section 3.2 and Appendix A.3). The threshold approximates the onset of shoulder rotation in the aperture experiment cited in Section 4.5.
We added a passage-width sensitivity analysis that varies the threshold while holding the layouts and movement tasks from Tables 1 and 3 fixed (Section 4.5, Figure 4). The scores at 60 cm match the main comparisons.
The main gain is that more previously infeasible movements become feasible. Among movements that passed in both the input and refined layouts, paths were 2.91 cm shorter on average (Appendix F.1, Table 8). The blinded study reports how two participants judged comfort for everyday use from floor plans (Table 9).