- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper presents GeoSupSplat, a feed-forward framework for sparse-view surface reconstruction from two input images using 2D Gaussian surfels. The method introduces separate appearance and geometry opacities over shared surfel geometry, together with scale-invariant depth, depth-to-normal, and keypoint-based 3D consistency supervision to improve geometric reconstruction. GeoSupSplat_Generalizabl The approach is evaluated on RealEstate10K and zero-shot transfer to ScanNet and Replica, where it reports improved surface reconstruction and mesh-rendering performance over several feed-forward Gaussian baselines.
Critical strengths
-
Clear motivation and coherent method design. The paper identifies the mismatch between appearance visibility and geometric visibility in feed-forward Gaussian surface reconstruction, and proposes a weakly decoupled representation together with complementary geometry supervision objectives. The overall methodological pipeline is easy to understand.
-
The paper evaluates the method on RealEstate10K as well as zero-shot transfer to ScanNet and Replica, and includes ablations on opacity decoupling, geometry supervision, extraction strategies, camera prediction, and depth/normal quality, providing a relatively comprehensive empirical study.
Critical weaknesses
-
The quantitative results contain internal inconsistencies that materially undermine confidence in the empirical conclusions. In Table 3, the shared-opacity configuration reports CD/PSNR/LPIPS of 0.494 / 18.28 / 0.268, whereas the corresponding ablation in Table 9 reports the same CD and PSNR but LPIPS = 0.260. More seriously, Table 7 reports Precision = 0.439, Recall = 0.194, and F1 = 0.408 for pixelSplat on Replica. Under the paper's stated definition , these values give , not 0.408. Even if F1 is computed per sample before averaging, implies , which is still incompatible with the reported 0.408. Since the main empirical claims rely heavily on quantitative superiority, these inconsistencies raise a substantial concern about the reliability of the reported results.
-
The paper's scale-related interpretation of the geometry supervision is not fully supported by its mathematical formulation. Eq. (9) is described as scale-invariant because globally rescaling the predicted depth is absorbed by the optimal alignment scale. However, rescaling the pseudo-depth as yields , so the magnitude of the supervision still depends on the arbitrary numerical scale of the pseudo-depth. A related inconsistency appears in the keypoint-based 3D loss: with and , globally rescaling the predicted depths changes only the ray-depth terms while the camera baseline remains fixed. Therefore, this loss constrains scene geometry relative to the normalized camera baseline and is not globally scale-invariant. These properties are more restrictive than the paper's claim that the geometry supervision enforces consistency without constraining scene scale.
Questions for authors
-
The quantitative results contain internal inconsistencies that undermine confidence in the empirical conclusions.
In Table 3, the shared-opacity configuration reports CD/PSNR/LPIPS of 0.494 / 18.28 / 0.268, whereas the corresponding shared-opacity ablation in Table 9 reports the same CD and PSNR but LPIPS = 0.260.
More seriously, Table 7 reports Precision = 0.439, Recall = 0.194, and F1 = 0.408 for pixelSplat on Replica. According to the paper's own definition,
directly substituting the reported Precision and Recall gives
rather than the reported 0.408. Moreover, even if F1 were computed per sample and then averaged separately from Precision and Recall, each sample satisfies , which implies
The reported F1 of 0.408 therefore remains incompatible with the reported Recall of 0.194 under the metric definition given in the paper. Since the paper's main claims rely heavily on quantitative superiority, these internal inconsistencies materially weaken confidence in the reliability of the experimental evidence.
-
The scale-related interpretation of the geometry supervision is not fully consistent with the mathematical formulation.
The paper motivates Eq. (9) as a scale-invariant depth objective. Let the rendered depth be and the pseudo-depth be , with
\frac{\sum_{u\in\mathcal M}\hat D_u\tilde D_u} {\sum_{u\in\mathcal M}\hat D_u^2+\epsilon}, \qquad \mathcal L_d = \frac{1}{|\mathcal M|+\epsilon} \sum_{u\in\mathcal M} (s^\star\hat D_u-\tilde D_u)^2 .$$ Ignoring the numerical stabilizer $\epsilon$, rescaling the prediction as $$\hat D \rightarrow a\hat D$$ gives $$s^\star \rightarrow \frac{s^\star}{a},$$ so the aligned prediction $s^\star\hat D$ remains unchanged. However, rescaling the pseudo-depth as $$\tilde D \rightarrow k\tilde D$$ gives $$s^\star \rightarrow ks^\star,$$ and consequently $$\mathcal L_d \rightarrow k^2\mathcal L_d.$$ Therefore, while the optimum is invariant to a global rescaling of the predicted depth, the magnitude of the supervision still depends on the numerical scale of the pseudo-depth. This is relevant because the paper explicitly motivates the loss by the unknown scale of the pseudo-depth. A related issue appears in the keypoint-based 3D consistency loss. For two matched pixels, Eqs. (12)--(14) compare $$X_a=C_a+d_a r_a,\qquad X_b=C_b+d_b r_b,$$ through $\|X_a-X_b\|_1$. If the predicted depths are globally rescaled by $k$, $$X_a-X_b = (C_a-C_b)+k(d_a r_a-d_b r_b).$$ Since the camera baseline $C_a-C_b$ is fixed in the normalized camera frame, this objective is not invariant to a global rescaling of the predicted depths. Thus, although it does not impose metric world scale, it does constrain scene geometry relative to the normalized camera baseline. This is more restrictive than the paper's statement that the objective enforces cross-view agreement without constraining absolute scene scale. -
It is difficult to disentangle the contribution of the proposed method from the strong external geometric priors used by the system.
GeoSupSplat fine-tunes a DA3-LARGE backbone with a DINOv2 ViT-L trunk, while also using a separate frozen DA3 model for pseudo-depth supervision and RoMa for cross-view correspondences. The resulting prediction network contains 456.5M parameters, compared with 12.0M for MVSplat and 13.3M for MeshSplat. Although the paper includes several internal backbone and teacher ablations, the main comparison does not control for the substantial difference in pretrained geometric priors and model capacity. Consequently, it remains unclear how much of the reported reconstruction advantage should be attributed specifically to the proposed weakly decoupled representation and geometry losses. -
The primary Re10K surface benchmark provides limited evidence for the generality of the reconstruction claims.
RealEstate10K does not provide ground-truth surfaces, so the paper constructs reference geometry using dense COLMAP reconstructions from only 50 selected scenes. The paper further states that candidate scenes are chosen to have sufficient camera motion, parallax, and texture for dense reconstruction. This introduces a nontrivial selection bias toward scenes that are favorable to classical multi-view reconstruction, while the evaluation target itself remains reconstructed pseudo-ground-truth rather than true surface geometry. Given the relatively small benchmark size, this limits how strongly the reported Re10K gains support broad claims about generalizable surface reconstruction. -
The claimed appearance/geometry decoupling is only partial even at the supervision level.
The central motivation is that appearance visibility should not determine geometric confidence, yet the geometry-supervision mask explicitly requires both appearance coverage and geometry coverage to exceed thresholds. Thus, whether a pixel receives geometric supervision still depends on the appearance-opacity pathway. This does not invalidate the method, but it weakens the conceptual interpretation that appearance and geometric confidence are cleanly separated. -
The strongest reconstruction claims rely on a scale-and-translation aligned evaluation protocol.
The default surface metrics remove a global scale and translation before evaluation. Under the raw protocol, GeoSupSplat still obtains the best CD and precision, but it does not achieve the best recall or F1. Therefore, the broad claim of uniformly superior reconstruction should be interpreted specifically as superiority in aligned shape quality rather than complete reconstruction accuracy in the original coordinate frame. -
Minor Presentation and Notation Issues.
The manuscript contains a noticeable number of presentation and notation issues. For example, there are several grammatical errors and awkward expressions, such as "which assigning each surfel separate appearance and geometry opacities" in the abstract, "Our method achieve state-of-the-art performance" in the contribution summary, and "the weakly decoupled model produce sharper RGB renderings" in the caption of Fig. 2. The capitalization of "Gaussian" is also inconsistent across the manuscript. There are also several notation and definition issues. In Eq. (17), the full objective includes the camera-loss weight , but the implementation details only specify , leaving unspecified. In addition, several symbols are reused for different meanings: denotes a view index in the main method but is later reused as the TSDF voxel size; is used for Gaussian color/SH coefficients and later as a correspondence index; and denotes Gaussian tangential scale as well as the global alignment scale. The stabilizer also appears in multiple equations without an explicit numerical value, and in the RGB rendering equation is not formally defined as the view-dependent color obtained from the spherical-harmonic coefficients. These issues do not by themselves determine my overall recommendation, but they reduce the precision, readability, and reproducibility expected from an ICLR submission.