- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper presents PanoLOG, a two-stage framework for large-scale outdoor reconstruction from panoramic images using 3D Gaussian Splatting. The method first performs global coarse reconstruction with explicit sky modeling and monocular depth supervision, followed by block-wise refinement using a Geometry and Gradient-based Partitioning Strategy (G²PS). G²PS constructs spatial boundaries based on camera geometry and a parallax-inspired uncertainty formulation, and assigns cameras to individual blocks using rendering-loss gradients. The authors also introduce Pano360, a panoramic outdoor reconstruction benchmark containing 5,637 images across four scenes. Experiments on Pano360 and two public panoramic datasets report competitive rendering quality and relatively compact models compared with existing Gaussian Splatting approaches.
Critical strengths
The paper addresses the challenge of spatial partitioning for large-scale panoramic Gaussian Splatting, where conventional frustum-based strategies are less effective.
The proposed Pano360 benchmark provides a useful evaluation setting, and the method achieves competitive reconstruction quality with relatively compact models.
Critical weaknesses
-
The central gradient-based partitioning mechanism lacks sufficient mathematical and methodological justification. Equation (10) defines camera–block importance using the average magnitude of rendering-loss gradients with respect to Gaussian positions. However, gradient magnitude is not necessarily equivalent to observational contribution or geometric visibility. A Gaussian may be highly relevant to a viewpoint while exhibiting a small positional gradient when the rendering residual is already low. Conversely, a large gradient may arise from reconstruction errors or parameter sensitivity rather than meaningful observational importance. This distinction is particularly relevant because the importance scores are collected after global coarse optimization. Furthermore, Equation (11) does not guarantee sufficient camera coverage for each spatial block or overlapping camera assignments between neighboring blocks. Nevertheless, the paper relies on these properties to motivate effective block-wise supervision and cross-boundary consistency. The claimed relationship between gradient-based allocation and coherent reconstruction is therefore not adequately established by the mathematical formulation. The geometry-based component also raises concerns. Equations (7)–(9) motivate spatial boundary expansion through parallax-related depth uncertainty, but Appendix A fixes the triangulation range factor to 5 across all scenes without explaining how the underlying angular uncertainty or tolerance is estimated. Consequently, the practical method appears closer to a baseline-dependent heuristic than to the explicitly uncertainty-driven formulation emphasized in the paper. These concerns directly affect the technical validity and novelty of G²PS, which is presented as the paper's central contribution.
-
The experiments do not adequately substantiate the claimed scalability or isolate the contribution of the proposed partitioning strategy. A central motivation of PanoLOG is to prevent panoramic block-wise reconstruction from degenerating into inefficient global optimization. However, Section 3.2.2 and Appendix D explicitly state that every block is initialized with the complete set of Gaussians from Stage I. Since the assigned cameras still provide full panoramic observations, it remains unclear how much of the global representation is rendered, differentiated, and optimized during refinement before opacity-based pruning and final spatial filtering. Restricting camera assignments and cropping the final Gaussian representation do not, by themselves, establish computationally localized optimization. Despite scalability being a central claim, the experiments do not report training time, peak GPU memory, total computational cost, or performance as the number of spatial blocks increases. Appendix A also describes separate global and block-wise training stages, while the experimental setup states that all methods use 30,000 iterations. The resulting total computational budgets are not sufficiently clarified. Consequently, the reported reductions in final model size cannot be interpreted as direct evidence of improved training scalability. The experimental attribution is also incomplete. On Pano360, competing large-scale methods use cubemap-converted perspective images, whereas PanoLOG employs native ERP rendering together with additional sky and depth supervision. Although component ablations are provided, the G²PS ablation is limited to a position-only partitioning comparison on one scene and does not separately quantify the contributions of geometry-based partitioning and gradient-based camera allocation. As a result, the current experiments demonstrate competitive reconstruction performance but do not convincingly establish that the proposed partitioning mechanism is responsible for the observed improvements or that it resolves the claimed scalability problem.
Questions for authors
-
What evidence supports using positional rendering-loss gradients as a reliable measure of camera–block observational contribution? Equation (10) uses gradient magnitude as the importance criterion, although this quantity depends on both rendering residuals and parameter sensitivity. How do the authors distinguish genuinely informative observations from regions with large reconstruction errors? In particular, how does the criterion behave for well-reconstructed regions whose positional gradients become small after Stage I? Can the authors provide controlled evidence showing that gradient-based allocation outperforms alternative camera-assignment criteria under comparable camera budgets?
-
Does Stage II actually achieve computationally localized optimization? The paper states that every block is initialized with the full Gaussian representation from Stage I. During block-wise refinement, are Gaussians outside the target block still rendered, updated, and considered for densification before opacity-based pruning? If so, how does the method avoid repeated optimization of substantial portions of the global scene? Can the authors report stage-wise training time, peak GPU memory, the number of actively optimized Gaussians, and computational scaling with the number of blocks? These measurements are essential for evaluating the paper's central scalability claim.
-
How is the uncertainty-based geometric partitioning implemented and validated? Equations (7)–(9) derive the partitioning margin from angular parallax uncertainty, but Appendix A specifies a fixed triangulation range factor across all scenes. Are the angular uncertainty and tolerated relative depth error explicitly estimated, or is the range factor selected empirically? If the latter, what establishes that the proposed strategy is genuinely uncertainty-adaptive rather than a camera-baseline-scaled heuristic? Additionally, can the authors disentangle the effects of geometry-based boundary construction and gradient-based camera allocation through controlled ablations?
-
Are the comparisons sufficient to attribute the reported improvements to G²PS under comparable computational budgets? The large-scale baselines operate on cubemap-converted images, while the proposed approach uses native ERP rendering and additional depth and sky modeling. How much of the reported improvement is attributable specifically to G²PS rather than these other differences? Were the total training costs, including both global optimization and independent block refinement, comparable across methods? A controlled comparison using consistent rendering and supervision configurations would materially affect the assessment of the proposed contribution.
5 comments
Responses to Reviewer kGfq, Q1-part2
Reply to Q1 (Part 2/2):
To validate the gradient-based assignment under the same camera budget, we match the number of cameras per block of only-position to that of G²PS: cameras outside a block are added from the block boundary outward, nearest first, until the block has the same number of cameras as under G²PS. The Stage I initialization, partition, ERP rendering, and supervision are identical.
Table 1: only-position with matched camera budget vs. G²PS.
| Scene | Setting | Cameras per Block | PSNR ↑ | SSIM ↑ | LPIPS ↓ | Size (MB) ↓ |
|---|---|---|---|---|---|---|
| NSC | only-position (camera-matched) | 40.29% / 73.33% | 27.69 | 0.845 | 0.258 | 458 |
| NSC | G²PS | 40.29% / 73.33% | 28.14 | 0.859 | 0.246 | 426 |
| NSK | only-position (camera-matched) | 52.98% / 59.92% | 24.15 | 0.812 | 0.198 | 623 |
| NSK | G²PS | 52.98% / 59.92% | 24.64 | 0.827 | 0.187 | 597 |
Here, the model size is an outcome of training rather than a controlled variable. The capacity-controlled comparison with only-position (without camera matching) and the full ablation of only-position / only-grad / G²PS are given in Table 7 in our reply to Q4.
We further compare with the rendering contribution based assignment. CityGaussian estimates the contribution of a camera to a block by removing that block and measuring the SSIM change of the rendered image. For ERP panoramas, a single camera has a 360° observation range, so different blocks all contribute to the whole image, and this measure may assign many cameras to multiple blocks. On NSC and NSK, we measured the fraction of all training cameras that each method assigns to each block.
Table 2: Camera assignment ratios of the SSIM-based and gradient-based assignments.
| Dataset | Block | SSIM Assignment | Gradient Assignment |
|---|---|---|---|
| NSC | Block 1 | 100% | 40.29% |
| NSC | Block 2 | 100% | 73.33% |
| NSK | Block 1 | 100% | 52.98% |
| NSK | Block 2 | 100% | 59.92% |
The SSIM-based assignment gives all training cameras to both blocks, whereas the gradient-based assignment produces more selective camera sets. Since the SSIM-based assignment loses its discriminative power, we did not proceed to Stage II training under it.
On the concern that gradients may become small after Stage I converges: we compute the gradient scores and the camera assignment from the C20K and C30K checkpoints (20K and 30K iterations) of the same Stage I run. To avoid the influence of the initialization quality of the coarse model, Stage II is always initialized from C30K; only the checkpoint used to compute the gradient score changes. The reported Jaccard is the Jaccard similarity of the camera sets under the two checkpoints, computed per block and averaged over blocks.
Table 3: Sensitivity to the coarse checkpoint.
| Dataset | Coarse Checkpoint | Jaccard ↑ | PSNR ↑ | SSIM ↑ | LPIPS ↓ | Size (MB) ↓ |
|---|---|---|---|---|---|---|
| NSC | C20K | 0.99 | 28.09 | 0.854 | 0.248 | 394 |
| NSC | C30K | 1 | 28.14 | 0.859 | 0.246 | 426 |
| NSK | C20K | 0.97 | 24.58 | 0.826 | 0.189 | 572 |
| NSK | C30K | 1 | 24.64 | 0.827 | 0.187 | 597 |
Between C20K and C30K, the camera-block assignment Jaccard reaches 0.99 on NSC and 0.97 on NSK, and the final PSNR differs by only 0.05 dB and 0.06 dB, respectively. Within the tested late training range, the gradient-guided camera assignment is therefore highly stable and does not change significantly as the coarse model is further optimized.
Responses to Reviewer kGfq, Q2
Reply to Q2:
We first clarify how Stage II is actually trained.
Every block is initialized from the complete Stage I coarse Gaussian model, but is refined only with the training cameras assigned to it. Since each ERP camera observes the full 360° environment, we keep the Gaussians outside the target block in the panoramic rendering and parameter updates instead of removing them before training. These Gaussians are optimized as well; whether they are updated and densified depends on their visibility and gradients under the cameras assigned to the current block.
This design keeps the panoramic rendering context complete. Removing the Gaussians outside the target block in advance would leave the other regions observed by the current camera without a representation, which could impair the supervision from the full panorama. After training, we keep only the Gaussians inside the spatial extent of each block and merge them into the final model.
We note that this process is not equivalent to strictly local Gaussian optimization. The Gaussians outside the target block still participate in training, so our method does not fully eliminate the repeated rendering and parameter optimization cost across blocks. The partitioning strategy mainly organizes the refinement of different regions through the assignment of camera sets, and the final spatial filtering avoids keeping duplicate copies of the full scene representation.
On computational efficiency, we report on NSK the training time, peak GPU memory, and number of active Gaussians with different numbers of blocks, together with the stage-wise computational cost. Coarse GS is the total number of Gaussians in the Stage I coarse model. Active GS is the number of Gaussians that, when a block loads the coarse model, are visible to the cameras assigned to that block and satisfy the densification criterion.
Table 4: Computational efficiency with different numbers of blocks.
| #Blocks | Block | Coarse GS (M) | Train Time (min) | Peak Mem (GB) | Active GS (M) |
|---|---|---|---|---|---|
| 2 | 0 | 1.93 | 35.9 | 7.6 | 1.23 |
| 2 | 1 | 1.93 | 36.7 | 7.8 | 1.02 |
| 4 | 0 | 1.93 | 38.1 | 5.2 | 0.88 |
| 4 | 1 | 1.93 | 42.8 | 5.4 | 0.90 |
| 4 | 2 | 1.93 | 40.0 | 5.0 | 0.78 |
| 4 | 3 | 1.93 | 36.3 | 5.9 | 0.56 |
Table 5: Stage-wise computational cost (NSK, 2 blocks).
| Stage | Time (min) | Peak Mem (GB) |
|---|---|---|
| Stage I | 39 | 11.8 |
| Partition | 8 | 3.2 |
| Stage II | 72.6 | 7.8 |
| Merging | 0.94 | 3.6 |
| Total | 120.54 |
These results show the actual training mechanism of PanoLOG, its computational cost, and how the number of blocks affects resource consumption.
Responses to Reviewer kGfq, Q1-part1
We thank the reviewer for their patience. This rebuttal involved a large number of additional experiments, which took some time to complete under limited GPU resources. We kindly invite the reviewer to read the additional results below, and we are happy to answer any further questions.
Reply to Q1 (Part 1/2):
In the paper, we state that the position gradient reflects the importance of a Gaussian to the current viewpoint: regions with large contributions exhibit large gradients, while distant or occluded regions have near-zero gradients. Here, "importance" means the strength of the optimization signal that the camera's photometric loss provides to the position parameters of the Gaussians in a block, not a direct estimate of physical visibility.
The gradient score of camera k for the Gaussians in block b is defined as
sk,b=∣Gb∣1∑g∈Gb∂xg∂Lk1,
with the same notation as Eq. (10) of our paper. From the volume rendering C=∑iciαi∏j<i(1−αj), we obtain
∂αn∂C=Tn(cn−Cn+),Tn=∏j<n(1−αj),Cn+=∑i>nciαi∏n<j<i(1−αj),
where Cn+ is the composited color of all Gaussians behind the n-th Gaussian. Hence Tn>0 (the Gaussian is not fully occluded) is a necessary condition for a non-zero gradient, since both terms contain Tn. It is not a sufficient condition: the gradient can be zero when cn=Cn+ (the Gaussian has the same color as the composite behind it), or when the pixel residual is zero, which gives ∂Lk/∂C=0. Conversely, a non-zero gradient implies that the Gaussian projects onto the valid pixel region of the ERP image, is not fully occluded, and makes a non-zero contribution to the pixels.
We do not treat this score as an exact measure of visibility, but as the strength of the optimization signal that the current model still needs under that camera's observation. We therefore do not attempt to distinguish "genuinely informative observations" from "large reconstruction errors": both mean that the current model is still sensitive to that observation, and both should receive optimization signal. The only difference is that converged regions with small gradients do not need additional cameras.
On the concern that well-reconstructed regions have small residuals and hence small position gradients: Eq. (11) uses the score normalized across blocks for the same camera, sk,b/maxb′sk,b′, not its absolute magnitude. When the overall gradient scale of a camera shrinks, its scores on all blocks shrink proportionally and the assignment is unchanged. The assignment Jaccard of 0.97 to 0.99 between C20K and C30K (Table 3) also indicates that the assignment is fairly stable within the tested range. More importantly, the geometric membership term of Eq. (11) guarantees that every camera is assigned at least to the block containing its center, so a well-reconstructed region still keeps all the cameras located inside it. The gradient term only determines which cameras from other blocks are additionally assigned, so small gradients affect only these "additional" cameras and do not deprive such regions of basic supervision.
On the coverage and overlap of Eq. (11): camera centers lie inside the AABB and the blocks form a partition of the AABB, so the geometric term leaves no camera unassigned and gives each block at least all the cameras located inside it. The gradient term then adds the cameras from other blocks whose normalized score exceeds τgrad. With the default 2 blocks, the camera coverage of the two blocks is 40.29%/73.33% on NSC and 52.98%/59.92% on NSK. Moreover, every block in Stage II is initialized from, and optimizes, the complete set of Stage I Gaussians, and is filtered by its spatial extent only at the end, so Gaussians near a block boundary are optimized jointly under the camera sets of the adjacent blocks. Even when the camera overlap is small, the shared initialization and two-sided observation help maintain cross-boundary consistency.