- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Bi-FlowGS to address insufficient geometric constraints in sparse-view 3DGS. It introduces V2G to refine Gaussian geometry using optical flow from restored videos and G2V to improve video restoration through geometry-guided flow, jointly enhancing reconstruction and rendering quality.
Critical strengths
-
Effective bidirectional refinement framework. The proposed V2G and G2V modules establish a bidirectional connection between generative view restoration and Gaussian geometry optimization, improving both rendering quality and geometric consistency.
-
Extensive experimental validation. The method demonstrates consistent improvements over several baselines across multiple datasets, supported by component ablations and geometric evaluations.
Critical weaknesses
W1. Limited comparison with recent SOTA methods. The paper omits comparisons with recent methods such as ArtiFixer[1], which also leverages video diffusion for sparse-view 3DGS reconstruction. This limits the assessment of its competitiveness against current state-of-the-art approaches.
W2. Unclear presentation of core contributions. The pipeline figure contains excessive details of existing architectures, such as attention mechanisms, while insufficiently highlighting the proposed V2G and G2V modules, making the actual contributions difficult to identify.
W3. Limited robustness analysis of generated optical flow. V2G relies on optical flow from generated videos, which may contain geometrically inconsistent or hallucinated content. Despite reliability filtering, the method's robustness to such errors remains insufficiently validated.
[1] R. de Lutio, T. Fischer, Y.-Y. Chang, Y. Zhang, J. Z. Wu, X. Ren, T. Shen, K. Tothova, Z. Gojcic, and H. Turki, “ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models,” in Proc. ACM SIGGRAPH, 2026.
Questions for authors
Q1. Comparison with recent SOTA methods. Could the authors provide comparisons with recent methods such as ArtiFixer under consistent evaluation settings to better demonstrate the competitiveness of Bi-FlowGS?
Q2. Robustness to generated flow errors. How does V2G handle geometrically inconsistent optical flow caused by hallucinated content in generated videos? Can the authors provide further robustness analysis?
8 comments
Response to Reviewer WQuL
Weakness2: Unclear presentation of the core contributions and redundant presentation of attention-mechanism details.
Answer:
We thank the reviewer for this constructive suggestion. To help you understand our pipeline diagram more clearly, we have improved its structure and explicitly labeled V2G and G2V to highlight the core contributions. The updated diagram appears in Figure 2 of the revised manuscript.
Regarding the attention-mechanism details, Flow-Biased Local Cross-Attention is a new module that we have added to the CogVideoX backbone. It uses flow-derived attention biases to transfer spatially aligned, fine-grained features from the first and last real reference images to each generated frame. Complementing geometry-aware motion guidance, it enriches texture details while maintaining motion consistency. We therefore retain this module in the pipeline diagram to illustrate how G2V jointly preserves motion consistency and local appearance fidelity.
Question2.1: How does V2G handle errors when hallucinated content in generated videos produces geometrically inconsistent flow?
Answer:
a. V2G incorporates a teacher-flow filtering mechanism that considers both temporal consistency and geometric validity. Specifically, the teacher-flow reliability term excludes matches with invalid warps, excessive motion, or large forward–backward cycle errors; the geometric reprojection mask further excludes occluded or geometrically inconsistent correspondences. The detailed design is provided in Appendix E.4.
b. Ablation Study Demonstrates the Effectiveness of the Flow Filtering Mechanism.
We conducted an ablation study of the filtering mechanism in the paper, providing preliminary evidence of its effectiveness. The following results are taken from Appendix E.4.
Ablation study of the flow filtering mechanism:
| Teacher Flow Reliability | Geometric Reprojection Mask | PSNR ↑ | SSIM ↑ | LPIPS ↓ |
|---|---|---|---|---|
| ✓ | ✓ | 15.643 | 0.502 | 0.468 |
| × | ✓ | 15.442 | 0.499 | 0.469 |
| ✓ | × | 15.454 | 0.498 | 0.470 |
| × | × | 15.480 | 0.499 | 0.468 |
Removing the V2G flow filtering mechanism clearly degrades the results, demonstrating the effectiveness of teacher-flow filtering.
Question2.2&Weakness3: Insufficient robustness analysis regarding flow errors.
Answer:
We sincerely thank the reviewer for this valuable suggestion. In response, we have conducted additional ablation experiments to evaluate the robustness of our method to erroneous optical flow. The experimental results and corresponding analysis are presented below.
(1) V2G effectively filters flow across different quality levels. To analyze the robustness of our filtering mechanism to erroneous flow, we categorize flow by quality and examine filtering performance at each quality level. Under the 6-view setting on Tanks and Temples, we randomly select three scenes, generate restored videos along the GT video trajectories using the video diffusion model, and estimate flow from the restored videos using WAFT. Based on LPIPS between the restored and GT videos, we divide restoration quality into Good (LPIPS ≤ 0.3619), Medium (0.3619 < LPIPS ≤ 0.4349), and Poor (LPIPS > 0.4349) groups and compare flow metrics before and after filtering.
The evaluation includes 1,793 valid frame pairs in total.
Flow filtering across different quality levels (units: pixels):
| Restoration Quality | Frame Pairs | LPIPS ↓ | FB Before ↓ | FB After ↓ | EPE Before ↓ | EPE After ↓ | Fl-all Before ↓ | Fl-all After ↓ | Masked Ratio |
|---|---|---|---|---|---|---|---|---|---|
| Good | 428 | 0.3276 | 2.184 | 1.286 | 2.836 | 2.615 | 25.48% | 13.72% | 26.20% |
| Medium | 976 | 0.4089 | 3.018 | 1.620 | 3.487 | 2.825 | 34.72% | 19.46% | 41.10% |
| Poor | 389 | 0.4932 | 3.996 | 2.430 | 4.964 | 3.277 | 50.65% | 32.18% | 59.30% |
| Overall | 1,793 | 0.4078 | 3.031 | 1.716 | 3.652 | 2.873 | 35.97% | 20.85% | 41.49% |
Filtering reduces FB Error, Geometric EPE, and Fl-all in all three quality groups, while the proportion of filtered matches increases as flow quality deteriorates. These results indicate that V2G is robust to flow of different quality levels. The corresponding experiment has been added to Appendix E.6.
Response to Reviewer WQuL
(2) Validating the Effectiveness of Flow Filtering through Reconstruction Comparison with GT Video Flow.
To further validate the effectiveness and robustness of V2G's flow filtering mechanism, we conduct reconstruction experiments on Tanks and Temples under the 6-view setting. We change only the source of teacher flow while keeping all other training procedures identical. Specifically, we feed the GT video frames and the diffusion-restored frames generated along the same GT camera trajectory into the same WAFT model, obtaining GT Video Flow and Ours Flow, respectively, and compare their reconstruction results.
Reconstruction comparison using different teacher-flow sources (one complete video-generation round):
| Teacher Flow | PSNR ↑ | SSIM ↑ | LPIPS ↓ | Surface F-score (%) ↑ | AbsRel ↓ |
|---|---|---|---|---|---|
| GT Video Flow | 15.92 | 0.557 | 0.446 | 14.03 | 0.05864 |
| Ours Flow | 15.83 | 0.556 | 0.449 | 11.23 | 0.08100 |
The two teacher-flow sources achieve comparable rendering quality. These results indicate that Ours Flow provides effective supervision and that V2G's flow filtering mechanism helps mitigate, to some extent, the impact of unreliable flow on final reconstruction, further demonstrating its effectiveness and robustness. We have added the corresponding experiment to Appendix E.5.
(3) Failure-case analysis. To analyze extreme teacher-flow failures, we reuse the experiment in (1) and evaluate the same 1,793 valid frame pairs. A frame pair with a mean EPE exceeding 5 pixels is defined as an extreme failure in this analysis. A total of 105 frame pairs (5.86%) meet this criterion, with a mean EPE of 8.141 px. After applying the reliability mask, 80.64% of valid geometric-evaluation pixels are discarded, leaving 45 frame pairs whose mean EPE decreases to 4.353 px. Among these 45 frame pairs, 15 pairs still have a mean EPE above 5 pixels.
Filtering of flow in extreme failure cases:
| Evaluation | Frame Pairs | Geometric EPE ↓ | Masked Ratio (Proportion of Discarded Flow) |
|---|---|---|---|
| Before Mask | 105 | 8.141 px | — |
| After Mask | 45 | 4.353 px | 80.64% |
Direct inspection of erroneous flow matches that pass filtering reveals why they can pass: paired frames may contain visually consistent content arising from shared hallucinations generated by the model. Consequently, the estimated pixel correspondences satisfy forward–backward consistency while remaining geometrically incorrect. We have also added visualizations of the corresponding flow failure cases in Figure 14 of the appendix.
These results show that the reliability mask removes most unreliable matches in extreme failure cases and reduces the geometric error of retained flow. We have added the corresponding experiment to Appendix E.6.
(4) Artificial perturbation analysis. To further verify robustness, we artificially add noise perturbations to the teacher flow before applying our reliability filtering. We then analyze the resulting reconstruction performance.
For each teacher-flow map generated during iteration, we randomly select a rectangular region covering approximately 10% of the image area. Within this region, we add a uniform offset to all flow vectors. The offset has a randomly sampled direction and a fixed magnitude of either 8 or 16 pixels.
All other reconstruction settings remain unchanged. We conduct reconstruction experiments under the 6-view setting on Tanks and Temples, evaluating four variants corresponding to the two perturbation magnitudes, with the reliability mask either retained or removed.
Reconstruction comparison with and without mask filtering under artificial teacher-flow perturbations:
| Experimental Variant | PSNR ↑ | SSIM ↑ | LPIPS ↓ |
|---|---|---|---|
| Ours | 15.93 | 0.555 | 0.437 |
| 8 px + Mask | 15.90 | 0.553 | 0.439 |
| 8 px, no mask | 15.76 | 0.547 | 0.446 |
| 16 px + Mask | 15.87 | 0.549 | 0.441 |
| 16 px, no mask | 15.68 | 0.539 | 0.455 |
With the reliability mask retained, perturbations have only a minor effect on reconstruction, and the resulting reconstruction performance is stronger than without mask filtering. These results demonstrate that our filtering mechanism maintains robust reconstruction performance across different flow quality levels. The corresponding experiment has been added to Appendix E.6.
We sincerely thank you again for your positive assessment and constructive suggestions. We hope that our responses have adequately addressed your concerns. Should you have any further questions or concerns, we would be more than happy to discuss them with you.
Response to Reviewer WQuL
We thank the reviewer for recognizing the bidirectional co-optimization framework and effectiveness of our method, as well as the comprehensiveness of our experiments. Below, we provide additional evidence and analyses addressing the weaknesses you raised.
Weakness1&Question1: Insufficient comparisons with the latest SOTA methods.
Answer:
We thank the reviewer for this helpful suggestion. To address your concern, we have added comparisons with ArtiFixer and plug-and-play experiments, as detailed below:
(1) Reconstruction comparison with ArtiFixer. We compare Bi-FlowGS with ArtiFixer on CO3D under the 3-, 6-, and 9-view input settings, strictly ensuring identical input views and test splits for both methods to enable a fair comparison. The results are presented in the following table.
Comparison with ArtiFixer on CO3D:
As shown in the results, ArtiFixer achieves stronger reconstruction performance under the extremely sparse 3-view input setting, possibly because the initial reconstruction is less complete, limiting the effectiveness of flow guidance and geometric supervision in Bi-FlowGS. As the number of input views increases, the advantages of Bi-FlowGS become more pronounced: our method improves all three metrics under the 6- and 9-view settings. These results demonstrate the competitiveness of Bi-FlowGS.
(2) Plug-and-play effectiveness of V2G on ArtiFixer. Following the plug-and-play evaluation protocol in Table 3 of the original manuscript, we further integrate V2G into ArtiFixer and conduct experiments on CO3D under the 6-view setting. The results are shown below. Geo. Avg follows the definition in Table 3 and denotes the average relative improvement across eight geometry metrics.
Plug-and-play results of V2G on ArtiFixer:
With V2G, all rendering metrics improve, with an average gain of 34.53% across the geometry metrics. These results extend the plug-and-play evaluation to ArtiFixer, supporting the applicability of V2G to another recent reconstruction framework.