- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper presents a training-free depth completion method that adapts the response coordinate for global metric calibration. It combines Box–Cox alignment with Hard-Dirichlet residual reconstruction to recover dense depth from a monocular prior and sparse observations.
Critical strengths
The formulation is compact and offers a well-motivated approach to depth-dependent calibration. The experiments cover multiple datasets and monocular priors, with stage ablations and an explicit discussion of the depth–normal trade-off.
Critical weaknesses
Adaptive calibration minimizes metric-depth squared error, whereas GLog and GDisp fit in their respective coordinates, confounding response flexibility with residual weighting (Eq. 17; Appendix A.4). Despite the reported gains across 45 prior–subset combinations, fixed-λ controls using the same metric objective and crossed ablations with an identical reconstruction backend are missing; the Poisson baseline also differs in constraints and solving resolution.
Questions for authors
-
How much benefit remains when λ is fixed to −1, 0, or 1 using the same metric objective and feasibility constraints, and all calibration variants share the same reconstruction backend?
-
Can you provide per-observation-mode results and anchor counts, clarify common valid samples, pixels, and failure handling, and quantify paired performance uncertainty with scene- or video-grouped analysis?
-
What evidence favors hard over soft or robust constraints under identical guidance, particularly for preserving normal quality and handling point-sampled, noisy, boundary-mixed, or misregistered observations?
-
How do you handle equivalent or weakly identifiable λ values, initialization sensitivity, and error amplification near the domain boundary, especially outside the observed depth range?
2 comments
Official Comment by Authors for Reviewer MJu5 (2)
Q4. Weakly Identifiable , Initialization Sensitivity, and Domain Boundaries
We thank the reviewer for the insightful question. We have done a few works to stablize the computation and avoid several degenerated cases.
-
Scale centering and numerically smooth transition (Eqs. 5–6, Appendix A.1): Normalizing by the anchor geometric mean enforces and for every , decoupling from overall global scale. Evaluating the power branch via
expm1and smoothly transitioning to the logarithmic branch when is tiny eliminates catastrophic cancellation near . -
Weak identifiability and parameter drift (Eq. 21): When the observed depth span is narrow or the underlying relationship is nearly linear, neighbouring tuples induce virtually indistinguishable monotonic curves over the observed interval. We address this weak identifiability via damped Levenberg–Marquardt optimization, accepting a step only when it strictly decreases the metric residual to suppress parameter drift.
-
Domain boundaries and out-of-range extrapolation (Appendix A.1): Because and is strictly increasing, is positive across the entire dense prior if and only if it is positive at the global extrema and . Checking positivity at these two endpoints before accepting every LM step prevents singularities and unbounded error amplification outside the observed depth range, resulting in 0 failures across all 45 combinations.
Official Comment by Authors for Reviewer MJu5
Dear Reviewer MJu5,
Thank you for the rigorous review and for highlighting our compact depth-dependent calibration formulation, broad evaluation across priors and datasets, and explicit analysis of the depth–normal trade-off. We have completed intensive experiments addressing the raised concern. Due to the limited computational resources and strict timeline, we report the depth completion performance metrics on a randomly chosen Barn dataset. We will also update the full results on a wider range of datasets in the revised version of the main paper.
Q1: Clarification on Fixed-Controls and Crossed Backend Ablations Thank you for suggesting a controllable experiments on different baseline involving representative λ. We report these results in the table below.
Under identical fitting objectives, feasibility constraints, and refinement backends, adapting λ reduces AbsRel by 63.4%–75.6% before completion and 47.7%–59.8% after Hard-Dirichlet completion. This indeed reveals the strong motivation of our proposed method. We will update the manuscript to include more discussion and related experimental results.
Q2: Per-Mode Results, Anchor Counts, Valid Pixels, and Failure Handling
We initially detailed this information on different parts in both the main paper and appendix (A.3, F, G.3, and H). Here we provide a more complete summary as below.
Samples: 3,698 images and 11,094 image–mode entries across 9 subsets.
Anchor counts: Median valid anchor counts per subset across the three modes (Distributed / Central removal / Outer removal) are reported in Table H (e.g., 4,207 / 2,275 / 1,941 on Barn).
Per-mode results (9-subset Macro p50 AbsRel): Ours achieves 0.0212 / 0.0344 / 0.0433; PriorDA achieves 0.0188 / 0.0353 / 0.0683; LDCM achieves 0.0163 / 0.0480 / 0.0731; Any2Full achieves 0.0190 / 0.0415 / 0.0640. Our gains are most pronounced under structured spatial missingness (Central and Outer removal).
Common valid pixels and failure handling: All methods are evaluated over the exact same pixel set (valid reference pixels inside the scoring mask, excluding anchor pixels). Ours records 0 failures across all 45 prior.
Q3: Hard vs. Soft/Robust Constraints under Identical Settings
Under identical Stage-1 parameters and gradient guidance, we replace exact Dirichlet elimination with a soft anchor penalty μobs∑(xp−logsp)2, and we report below the depth completion performance on Barn dataset.
From these results one can summarize as
We also want to enhance the conclusion by mentioning the experiments suggested by Reviewer rKr7 with lidar-scan-like noise. Under heavy measurement noise (4 cm/12 cm), replacing hard elimination with a soft constraint (μobs=0.5) lowers p50 AbsRel from 0.0178 to 0.0147.
We will revise the main paper to report both findings in the noise-rich and noise-sparse cases for hard/soft constraints.
message follows.