- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies dense scene completion from a single sparse LiDAR scan and proposes BeamScene, a single-pass framework that uses an approximate beam footprint, derived from range and sensor angular resolution, to coordinate candidate generation, feature-scale selection, and geometric supervision. The framework contains three main components. BFCC allocates a fixed candidate budget according to footprint area, expands candidates in ray-orthogonal planes, and preserves input observations as immutable anchors. FASSE shares sparse convolutional kernels across voxel scales and input branches, combining features through footprint-dependent scale weights. FRVO introduces training-only supervision based on local optimal transport, first-return consistency, and a free-space penalty. An observation-preserving coarse-to-fine decoder produces the completed point clouds. The paper evaluates the method on SemanticKITTI and tests transfer to KITTI-360 without fine-tuning. The coarse model’s main gains over LiNeXt occur in fine-resolution voxel IoU, alongside a 43.7% reduction in parameters. The refined model achieves the best reported results across all six metrics among the compared methods on both datasets. Component ablations, internal design ablations, and efficiency comparisons provide further evaluation.
Critical strengths
-
Meaningful completion improvements with substantially fewer parameters. On SemanticKITTI, the coarse model improves [email protected] from 19.45 to 24.91 and [email protected] from 6.30 to 8.74 relative to LiNeXt, while reducing parameters from 1.99M to 1.12M. Evaluation on KITTI-360 without fine-tuning shows improvements in the same direction. This establishes practical value through improved geometric recovery alongside parameter reduction. The latency reduction relative to LiNeXt is modest; the principal efficiency benefits are parameter savings and substantial acceleration relative to diffusion-based methods.
-
The architecture incorporates useful engineering properties. Exact preservation of input observations, control over output cardinality, and restriction of additional visibility supervision to training are meaningful design choices. They make the relationship between measured and generated geometry explicit while maintaining a straightforward inference pipeline. The appendix also helps clarify which properties follow directly from construction and where the method’s guarantees end.
Critical weaknesses
-
The central physical-consistency claim lacks direct validation, and the FRVO surrogate has potentially consequential limitations. Section 3.5 and Table 4 define “rays” using angular bins, which are substantially coarser than the nominal angular resolution used by BFCC. A single bin can contain both foreground and background surfaces, so its minimum range does not directly represent the first return along every direction within that bin. Furthermore, the reference geometry comes from aggregated scans, and the loss involves point subsampling. It remains unclear how these operations preserve reliable free-space evidence from the input viewpoint. The free-space term in Eq. (6) constrains a softmax-weighted average range. Consequently, an early point can be diluted by sufficiently many slightly farther points. For example, using the paper’s temperature, a bin containing one point at 9.8m and 127 points at 10m has a soft first return of approximately 9.989m. With a reference range of 10m and a tolerance of 0.1m, the one-sided free-space penalty is zero despite the point appearing 0.2m before the reference. This is an illustrative example derived from the formula, not an observed experimental result, but it demonstrates a possible failure of the surrogate. The authors acknowledge that inference-time consistency is not guaranteed. My concern is the absence of direct validation: CD, JSD, and IoU do not establish whether actual free-space violations or first-return errors decrease. The experiments support improved completion metrics, but the central physical interpretation remains insufficiently substantiated.
-
The internal ablations do not sufficiently establish the necessity or specific benefits of the unified footprint prior. In Table 2(c), replacing footprint routing with uniform weights improves IoU at all three voxel resolutions, including an increase in [email protected] from 8.74 to 9.44, and also improves JSD 3D. In Table 2(d), CD + FT achieves an [email protected] of 9.52, exceeding the full objective. The authors appropriately acknowledge these trade-offs. Nevertheless, because fine-resolution occupancy is a central motivation and headline result, the selection of the final configuration needs stronger justification. Additionally, under uniform angular resolution, the common factor cancels when the clipped footprint areas are normalized into allocation weights. Candidate-count allocation therefore reduces to bounded range-squared weighting. Angular resolution still affects expansion radius and scale routing, but candidate-count allocation itself has limited sensor specificity. Together with the absence of repeated-run variability, these results leave uncertainty about whether the full physical design offers stable advantages over simpler alternatives.
Questions for authors
-
Validity of visibility supervision: How do you handle foreground/background mixing within an angular bin and subsampling that omits the nearest point? Can you report free-space violation rates and first-return errors evaluated using the input’s actual observed rays, comparing LiNeXt, the full model, and the model without the Ray term? This would directly affect my assessment of the physical-consistency contribution.
-
Configuration selection and stability: Given that uniform scale weighting and CD + FT outperform the full configuration on several important metrics, what criterion determined the final design? Are the key differences in Table 2 stable across repeated training runs, using consistent training budgets and model-selection procedures?
-
Specific role of footprint modeling: Do you agree that uniform angular resolution cancels from the candidate-count allocation weights? After adaptive voxel downsampling to 18,000 input points, how does the nominal sensor footprint correspond to the actual input sampling spacing? Which existing results distinguish the benefits of footprint modeling from those of a generic range-adaptive strategy?
4 comments
Response to Reviewer khLs (2/4)
W1 / Q1 — Validity of the visibility supervision (cont.)
(d) The dilution example is correct, and its extent is bounded. We confirm the arithmetic: m, and the free-space penalty is zero. From Eq. (6), a single point at depth in front of escapes the penalty only if at least
other points in the same ray lie at . Points placed farther behind dilute less, so this is the minimum. With m (Table 4), this requires 8 points for m, 41 for 0.3 m and 164 for 0.4 m. Because the ray term keeps at most 128 points per ray (App. A), your example of points sits exactly at the cap. A violation deeper than about 0.38 m cannot be masked in any ray. For scale, 16,384 points spread over the roughly field of view give about 1.7 points per bin on average, far below the 8 points needed to mask even a 0.2 m violation. A masked shallow violation is also still penalised by the other two terms: the point pays its distance to the nearest reference point, at most 0.2 m, in the Chamfer term, and pays the radial cost of frustum-local transport, Eq. (5). Dilution therefore lowers the sensitivity of one term to shallow violations in dense rays; it does not create a blind spot in the objective. The direct evaluation in (e) measures the net effect on actual violations. The revised PDF adds your example and this bound to Appendix C (referenced from Sec. 3.5). It also notes that a per-point hinge removes dilution entirely.
(e) Direct validation on the input's actual rays. Following your suggestion, we evaluate on the k rays of each raw scan that are not among the 18k input points, i.e., observations the model never sees. A ray has a free-space violation if a predicted point lies within its beam cone (0.001 rad), at a range below , and farther than m from every reference point. The last condition excludes points on real surfaces, which at grazing incidence span a long range interval within the cone. A ray has a missing first return if no predicted point lies within of its measured return. Both rates are computed over all evaluated rays. Predicting fewer points would lower the violation rate but raise the missing rate, so the two are read together. All models are coarse (without refinement, as in Table 2), with comparable output sizes (k–180k points). Statistics are pooled over all frames of seq. 08. As a sanity check, the raw scan itself scores 0 on both metrics.
Table R5. Visibility on unseen raw-scan rays, SemanticKITTI seq. 08 (coarse models, all frames).
| Method | Free-space violation (%) @0.1 m / 0.2 m / 0.5 m | Missing first return (%) |
|---|---|---|
| LiNeXt | 0.63 / 0.60 / 0.51 | 36.16 |
| BeamScene, CD only | 0.59 / 0.57 / 0.48 | 35.30 |
| BeamScene, CD + FT (w/o ray term) | 0.54 / 0.53 / 0.46 | 34.67 |
| BeamScene (full) | 0.56 / 0.51 / 0.43 | 34.39 |
Three observations:
- BeamScene reduces actual violations relative to LiNeXt by 11–16% at every threshold, and lowers the missing rate by 1.8 points. On the 18k input rays, BeamScene's missing rate is exactly 0 by Prop. 2, whereas LiNeXt displaces measured points.
- Adding the ray term lowers deep violations without increasing missing returns. Compared with CD + FT (w/o ray term), violations decrease at 0.2 m () and 0.5 m (), and the missing rate also decreases slightly (), so the reduction does not come from predicting fewer points. These differences are 0.02–0.03 percentage points from a single training run. We read them as consistent with the design of Eq. (6), not as established, and include this evaluation in the three-seed runs (W2).
- The shallow band behaves as Eq. (6) implies. At 0.1 m, the full model is slightly higher (0.56 vs. 0.54%), i.e., violations shift from m into the 0.1–0.2 m band. The free-space penalty is a squared hinge that starts at m, so it acts weakly on violations just beyond 0.1 m and strongly on deep ones.
Response to Reviewer khLs (3/4)
W1 / Q1 — Validity of the visibility supervision (cont.)
Under this strict definition, violations are rare () for all methods. We therefore read the comparison as consistent relative reductions, not as a large absolute gap. The revised PDF adds this table (Table R5) to Sec. 4.3, and states explicitly that “physically consistent” refers to how the pipeline is constructed (Sec. 1, L100–104); FRVO encourages the visibility property, as measured above, but does not guarantee it at inference (Sec. 4.5, App. B).
W2 / Q2 — How the configuration was selected, and stability
We agree that in Table 2(c)/(d) the full model is best only in CD and JSD BEV.
- Selection criterion. The full configuration was fixed from the footprint model before any evaluation, and sequence 08 was never used to select it. Rows (b)–(d) ablate this design afterwards; they are not candidates in a search. Our protocol (Sec. 4.1: train on 00–07 and 09–10, evaluate on 08) has no held-out validation split, so switching to the best-scoring row on sequence 08 would select on the test split, and we did not do so. The fixed configuration happens to be best in CD, the only metric reported by every baseline (Table 1), and in JSD BEV, the global layout metric, while the two variants are better in fine IoU.
- The comparison with LiNeXt does not depend on this choice. Both alternatives beat LiNeXt (19.45 / 6.30 at 0.2 / 0.1 m) by more than the full model does: uniform scale weighting (“w/o footprint routing” in Table 2c) reaches 25.51 / 9.44 and CD + FT reaches 25.70 / 9.52, against 24.91 / 8.74. Within Table 2, the largest fine-IoU effects come from BFCC and frustum-local transport: removing BFCC gives the lowest [email protected] m among the single-component removals (7.68), and frustum-local transport adds over CD only. The footprint gate and the ray term trade some fine occupancy for CD and BEV layout, which Sec. 4.3 (L425–431) already describes as regularisation rather than a uniform gain. These are marginal effects, each measured with the other components present, and they do not account for the whole gain over LiNeXt at 0.2 m; the final version adds a cumulative ablation that starts from LiNeXt retrained in our implementation. The revised Sec. 4.3 states the selection criterion and presents uniform scale weighting and CD + FT as alternative operating points; the attribution will be stated in the contribution list of the final version.
- Stability. We agree that the submission lacks repeated runs. All variants follow the identical schedule in App. A (10 coarse epochs, the same optimiser and learning rate, batch size 16) and are evaluated at the final checkpoint, with no checkpoint selection on the test split. Variance estimates are therefore needed here. The largest component-level effects are clear: removing FRVO raises CD from 0.205 to 0.224, and removing BFCC lowers [email protected] m from 8.74 to 7.68. The smaller differences are not: removing FASSE changes CD by 0.003, the same size as the CD differences between the full model and the two variants (0.002 and 0.005), and the gaps between the full model and CD + FT in (e) are 0.02–0.03 percentage points. For fixed checkpoints, a paired block bootstrap over the scans of sequence 08 shows that the differences between the full model and these two variants hold consistently across scans (all 95% intervals exclude zero). This does not measure variation across training runs, so we do not claim that these smaller differences would persist under retraining, and we have worded the corresponding conclusions accordingly. For the final version, we will train the full model, uniform scale weighting, CD + FT and the three single-component removals of Table 2(a) with three seeds each, and report mean std for Table 2 and for the visibility evaluation in (e).
Response to Reviewer khLs (4/4)
W3 / Q3 — What footprint modelling specifically contributes
We agree that angular resolution cancels. Under uniform resolution, , and the quantile bounds scale by the same constant. Hence , and candidate allocation is bounded range-squared weighting. The revised PDF states this in Sec. 3.2 and no longer describes the allocation as sensor-specific. Our claim is narrower: is not a tuned schedule but the area law of constant-angle sampling. The range-adaptive rule used in prior work, LiNeXt's range groups, is a much flatter step function (5 to 15 copies, a factor of 3) with group boundaries and counts set by hand, whereas BFCC assigns between 1 and candidates per return.
Where angular resolution does matter. Above , Eq. (1) gives . The angular resolution sets the offset of the range-to-scale mapping shared by the expansion radius in Eq. (2) and the gate in Eq. (3), i.e., which voxel size is preferred at which range. With the values in Table 4 (, m), the gate peaks at 0.04 m at 10 m and at 0.16 m at 40 m. Without the sensor model this offset would be another hyperparameter. For sensors with non-uniform or per-beam resolution, varies across returns and no longer cancels from the allocation (Limitation 1).
Nominal footprint vs. the spacing of the 18,000 input points. By definition is the approximate area that one beam covers at range under the nominal angular resolution (Eq. 1). For example, at 10 m the nominal beam spacing is and cm. If the downsampling keeps a fraction of the returns near range , the actual area per retained return is . The footprint therefore matches the input spacing up to the retention ratio. Allocation is exactly area-proportional when does not depend on range, and only relative weights enter it, so a uniform thinning has no effect. If voxel downsampling removes proportionally more near-range points, the effective area grows more slowly than at short range. The lower quantile clip () flattens exactly that end of the distribution. Routing is soft by design: with , about 70% of the weight falls on two adjacent resolutions, so it does not require to match the spacing precisely. We will add this discussion, and the correction as a direct extension, in the final version.
Which existing results separate footprint modelling from a generic range-adaptive rule.
- Allocation. Table 2(b), “distance-grouped allocation”, isolates exactly this comparison: the tangent-plane expansion, encoder and loss are kept, and footprint allocation is replaced by LiNeXt's manually defined range groups (range quartiles with 5/8/12/15 copies). The law is better on all six metrics, mainly in global layout (CD , JSD BEV ) and only marginally at [email protected] m (). Within BFCC, the larger fine-IoU effect comes from the tangent-plane expansion (isotropic expansion: 8.42).
- Routing. Our ablation compares the footprint gate only with uniform scale weighting, which do not depend on range. It does not separate the gate from a range-based gate with a hand-tuned offset, and we do not claim it does. We will describe the gate as range-adaptive routing whose offset comes from the sensor model instead of tuning.
Summary of revisions
Already in the revised PDF (marked in blue).
- Sec. 3.5 and Appendix C: the conservative reading of FRVO for the full reference, the effect of point subsampling, the justification for bins, and your example with the masking bound.
- Sec. 4.3: the input-ray visibility evaluation in (e) (Table R5), with its protocol in Appendix C.
- Sec. 4.3: an explicit selection criterion, with uniform scale weighting and CD + FT as alternative operating points; Appendix C: paired confidence intervals (Table R7).
- Sec. 3.2: the reduction of allocation to clipped weighting under uniform resolution.
We thank the reviewer again; the questions have clarified the scope of our physical-consistency claim, and we are happy to discuss further.
Response to Reviewer khLs (1/4)
We thank the reviewer for a careful review that engages with our equations directly. Several observations are correct as stated, and we address them using the formulation and results in the paper, together with a new direct visibility evaluation. Tables are numbered consistently across our responses to all reviewers. We have uploaded a revised PDF in which all changes are marked in blue; the new tables keep the numbering of this response (Tables R1–R7, with R2 and R5 in the main text and the others in Appendix C). Items that need new experiments or renderings (three seeds, the cumulative ablation from LiNeXt, the new insets in Fig. 5, and cross-sensor evaluation) will be added in the final version.
(a) Mixed foreground/background bins make the free-space penalty conservative. In Eq. (6), the reference first return of a bin is rb⋆=miny∈Yb∥y∥, the nearest surface anywhere in the bin. Every direction in the bin passes through [0,rb⋆) without a return, whichever surface it eventually hits. The free-space penalty acts only on predictions in [0,rb⋆−δf), so it never penalises a prediction at a range where some ray in the bin was blocked. Mixing has one effect: in a bin containing a foreground surface, the free space in front of the background directions, between the two ranges, is left unconstrained. In other words, the coarse bin leads to missed penalties, not wrong ones. This holds for the full reference; subsampling is discussed in (c).
(b) Relation to the input viewpoint after aggregation. The reference is built by aggregating neighbouring scans and removing dynamic objects (Sec. 4.1). Following LiDiff, moving objects are removed from the input scan with the same labels, so every input return lies on a static surface that the reference contains. For the full reference, in any bin that contains input returns, rb⋆ is therefore at or before each of those returns. Each input ray certifies [0,rin)⊇[0,rb⋆) as empty. The penalised region is therefore a subset of the free space observed from the input viewpoint, up to registration error, which δf absorbs. Aggregation can only move rb⋆ closer, which shrinks the penalised region and never enlarges it. In bins with no input return, the free-space penalty enforces only consistency with the supervision target (“no reference surface in front of rb⋆”). The revised Sec. 3.5 states this distinction.
Why 1∘×1∘ rather than the nominal resolution. The ray term (first-return term plus free-space penalty, Eq. 6) uses only bins that are non-empty in both sets, after each set is capped at 16,384 points (App. A). At the nominal angular resolution of 0.20∘×0.42∘ used by BFCC there are about 1,800×64≈115k directions, so on average 0.14 points per direction, and almost no direction would be occupied in both sets. A 1∘×1∘ bin, about 5×2.4 beam spacings at nominal resolution, is roughly the finest grid at which common rays exist in useful numbers. As App. A states, the FRVO partitions are intentionally independent of the BFCC discretisation.
(c) Subsampling. The ray term caps both the predicted and the reference sets at the same budget before binning, so omitting the nearest point affects both first-return estimates alike in expectation, but not in a given bin. With about 1.7 points per bin on average (see (d)), the subsampled reference minimum can lie behind the nearest reference surface. Because the free-space penalty is one-sided, such fluctuations do not average out: they can penalise a prediction that lies on the nearest surface. Subsampling can therefore introduce wrong penalties, and the conservative reading in (a) and (b) holds for the full reference only. The revised Sec. 3.5 states this. Keeping the nearest reference point of each bin when subsampling would remove the effect at no extra cost. The net effect of the objective on actual violations is measured directly in (e).