- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper proposed a method called Revisable 3D Scene Graph Generation (ReSGG). It's an plug-and-play module that allows historical observation-to-node assignments to change online as new views provide evidence. It is evaluated on 3DSSG and ReplicaSSG, Recall@1 improves by 16.4 and 13.0 percentage points over FROSS and NoPA on 3DSSG, and by 4.6 and 5.7 points on ReplicaSSG, with mean per-frame latency between 20.57 and 26.78 ms
Critical strengths
- The paper try to solve an important and common problem in online 3D scene graph generation: early false merges and splits can corrupt subsequent object fusion and relation aggregation. By combining historical observation regrouping with relation endpoint repair, the authors propose a well-motivated mechanism for correcting these errors during online processing.
- On 3DSSG, SGReviser improves relation Recall@1 from 28.4% to 44.8% for FROSS and from 53.3% to 66.3% for NoPA, with consistent gains on ReplicaSSG. The ablations also support the contribution: removing inter-fragment evidence reduces relation Recall@1 from 44.8% to 32.9%.
Critical weaknesses
- The revision criterion relies on depth and geometric alignment, which may limit its robustness under noisy real-world observations. The main experiments use rendered depth and benchmark poses. The ORB-SLAM3 ablation is useful, but it retains rendered depth and therefore does not establish robustness to sensor noise and pose errors occurring together.
- Long-term scalability remains insufficiently evaluated. Historical observations and relation records accumulate throughout processing, and revision uses the complete histories of participating nodes. Further analysis of how revision cost and correction delay scale with history length would strengthen the evidence for sustained online operation.
Questions for authors
- How sensitive is the revision criterion to depth noise?
- How do revision time and write-back delay scale with the length of the observation history?
2 comments
Thanks for the response and the updates about depth noise and history scaling. My concerns have been resolved. I will keep my score because it's already positive.
Response to GpZ3: Depth Noise and History Scaling
We thank the reviewer for the positive assessment and the focused questions. A revised PDF with changes highlighted is uploaded.
W1 / Q1. Sensitivity to depth noise. We agree that the ORB-SLAM3 ablation isolates pose error and does not cover sensor noise. Three design choices limit noise effects, though they do not remove them:
Noise larger than δ=5 cm can still turn depth agreement into free-space contradiction and reverse the sign (App. L). We add (a) a sweep with depth-dependent noise σ(z)=kz2, 5% pixel dropout, and boundary jitter; (b) raw 3RScan sensor depth (
*.depth.pgm), which the benchmark replaces with rendered depth; and (c) sensor depth with ORB-SLAM3 poses:We also test a depth-adaptive tolerance δ(z)=δ0+3σ(z) under the above noise conditions at k=0.005 and δ0=0.05 m. Fixed → adaptive tolerance gives Rel. 35.3 → 38.9, sRel. 23.5 → 24.2, preference precision 82.1 → 85.6, and abstention 49.2 → 45.2.
W2 / Q2. Scaling with history length. One revision has four cost components:
Regions larger than Bsync run in the background, so long histories mainly appear as write-back delay: 1.5% of revisions run in the background, with a median delay of 3 frames [IQR 1, 6] over 157 sequences (Tab. 25).
(i) Cost by region size (all revision events):
(ii) Long-run test. We concatenate each test trajectory in alternating forward and reverse order to L times its original length. All copies of a source frame are held out together, so a replayed frame never explains its own original. We also test a bounded-history variant that keeps at most Hmax=250 observations per node, selected by coverage gain:
Foreground P95 latency is the median of per-sequence P95 values.
Bounded history and backlog management were future work in Sec. 5. The revised paper reports these results and their limits.
We thank the reviewer again and are happy to answer any further questions.