- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
VIREO addresses the challenges of viewpoint-dependent recognition and redundant observations in aerial object navigation. It learns viewpoint-conditioned models of VLM responses, selects viewpoints based on expected information gain, and aggregates recognition evidence using geometric novelty weights. Experiments on UAV-ON, supported by online ablations and offline verification analyses, demonstrate promising improvements in overall navigation performance.
Critical strengths
-
The motivation is supported by empirical observations. Table 3 shows that 54.72% of matching object–description pairs produce mixed recognition responses across viewpoints. This provides concrete support for accounting for viewpoint when verifying candidate objects.
-
The framework coherently links viewpoint selection with candidate verification. Sections 3.3–3.5 use a shared response model to score prospective observations and update candidate beliefs. The controlled online ablation study in Table 4 supports the usefulness of both components within the same navigation system.
-
The supplementary evaluation strengthens the empirical contribution. Appendices B–C include verification on held-out scenes, calibration metrics, and bootstrap analyses grouped by object. The paper also explicitly acknowledges the movement-cost trade-off reported in Table 7 and distinguishes the calibration of candidate identity beliefs from navigation success.
Critical weaknesses
-
Section 3.5 downweights observations from similar camera positions and viewing directions, assuming that they provide redundant evidence. However, the paper does not examine whether similar viewpoints produce correlated recognition errors. Table 3 reports response variation across viewpoints, while Table 6 evaluates final belief calibration. Neither directly tests the relationship between geometric similarity and evidence redundancy.
-
The response model in Section 3.3 predicts VLM responses using relative camera geometry. It does not explicitly account for candidate appearance, distance to the candidate, or occlusion, all of which can affect a viewpoint’s usefulness. The paper does not report response-prediction accuracy or test whether higher information-gain scores identify more informative views on held-out scenes. Both viewpoint selection and belief updates depend on this model.
-
In Table 4, enabling evidence aggregation (EA) changes both observation weights and the rules for candidate acceptance and rejection. Consequently, the improvement cannot be attributed specifically to geometric weighting. The policies in Appendix B may also use different observations and stopping times. Controlled comparisons with unit weights and constant weights, using the same response model and decision rules, are needed to isolate the contribution of geometric weighting.
Questions for authors
-
Do geometrically similar viewpoints produce more strongly correlated recognition errors? Can you provide measurements from the collected observations to support the weighting rule in Section 3.5?
-
How accurately does the response model predict VLM judgments on held-out scenes? Do viewpoints with higher predicted information gain provide more useful evidence for distinguishing targets from non-targets?
-
Does geometric weighting outperform unit weighting and constant discounting when the response model and the rules for candidate acceptance and rejection are held fixed?
5 comments
The response of weakness_2 and question_2
W2 & Q2: Response Prediction and Viewpoint Utility.
Response: Our held-out-scene results show improved response prediction for true candidates, while the full viewpoint score improves true-candidate acceptance and observation efficiency in saved-observation verification.
(a) Response prediction.
We compare a constant-response model with the geometry-conditioned model over five scene-disjoint folds, keeping training, parameter-selection, and test scenes separate. Each candidate type contains 5,088 observations. The models predict the VLM's binary response, evaluated using NLL, Brier score, and ECE. For response and predicted positive-response probability , NLL averages , and Brier averages . ECE measures the frequency-weighted calibration gap over ten equal-width probability bins. Lower scores are better.
Constant predicts a fixed positive-response probability for each candidate type, independent of viewpoint.
Geometry predicts this probability from viewpoint geometry. Both models predict VLM responses.
The table below reports VLM response prediction on held-out scenes:
| Candidate | Model | NLL ↓ | Brier ↓ | ECE ↓ |
|---|---|---|---|---|
| Matching | Constant | 0.61405 | 0.20931 | 0.09943 |
| Matching | Geometry | 0.60885 | 0.20620 | 0.07254 |
| Non-matching | Constant | 0.33648 | 0.08457 | 0.06263 |
| Non-matching | Geometry | 0.30126 | 0.07465 | 0.04683 |
For both matching and non-matching candidates, conditioning on viewpoint geometry yields lower NLL, Brier score, and ECE than fixed-probability prediction, indicating more accurate and better-calibrated predictions of VLM responses.
(b) Viewpoint selection.
We replay saved observations for 424 objects and 848 matching/non-matching candidates. All selectors share the response model, evidence weights, initial view, initial belief of 0.5, decision thresholds of 0.95/0.05, and a six-observation budget including the first image. We vary only the next-view selector: predicted information gain multiplied by geometric novelty, novelty alone, or uniform random selection. Random selection is averaged over 64 repeats per candidate before object-level aggregation.
The full score combines predicted mutual information with novelty . For current belief and predicted positive-response probabilities and under target and non-target identities, respectively,
where .
TAR and FAR are the fractions of true and non-target candidates accepted, respectively. The undecided rate covers candidates without a decision after six observations; mean observations counts views until a decision or budget exhaustion.
The table below reports candidate verification under alternative view selectors:
| Selector | TAR (%) ↑ | FAR (%) ↓ | Undecided (%) ↓ | Mean views ↓ |
|---|---|---|---|---|
| MI × novelty | 79.01 | 6.60 | 7.19 | 2.71 |
| Novelty only | 75.94 | 7.08 | 8.25 | 2.77 |
| Random | 65.90 | 11.61 | 10.17 | 3.28 |
Compared with random selection and novelty-only selection, the full score increases TAR by 13.11 and 3.07 percentage points, respectively. It also yields lower FAR and undecided rates, while requiring approximately 17.4% fewer observations than random selection. These results support the effectiveness and efficiency of combining predicted information gain with geometric novelty for candidate verification.
We have included the held-out-scene response prediction and viewpoint-selection comparison in Appendix A.5, “Response Prediction and Viewpoint Selection” (Tables 13–14) of the revised manuscript.
The response of weakness_3 and question_3
W3 & Q3: Independent Contribution of Geometric Weighting.
Response: Geometric novelty weighting achieves higher SR, OSR, and SPL than unit weighting, fixed discounting, and visual-content-based weighting in the controlled online comparison.
We replace only the evidence-weighting rule, fixing the response model, viewpoint planner, candidate acceptance/rejection rules, and other components. All methods use Qwen3-VL-plus, RGB observations, official target descriptions, the same 200-task subset, a 150-action limit, and the same API-call rules per planning step.
The table below summarizes the alternative evidence-weighting rules:
| Weight | Weighting rule |
|---|---|
| Unit | All observations retain a weight of 1 |
| Fixed discounting | Each new observation starts at 1; earlier evidence weights decay by a factor of 0.5 per subsequent observation |
| RGB | Novelty based on RGB pixel similarity between the current and previous images |
| ResNet18 | Novelty based on frozen ResNet18 feature similarity between the current and previous images |
We evaluate SR, OSR, and SPL through closed-loop navigation. The table below reports online navigation performance under alternative weighting rules (%):
| Weight | SR ↑ | OSR ↑ | SPL ↑ |
|---|---|---|---|
| Geometry | 25.50 | 37.00 | 17.41 |
| Unit | 17.00 | 32.50 | 12.27 |
| Fixed discounting | 13.50 | 29.50 | 10.72 |
| RGB | 18.50 | 33.00 | 11.89 |
| ResNet18 | 13.50 | 34.50 | 8.66 |
The higher navigation metrics support the contribution of geometric weighting with the response model and candidate-decision rules held fixed.
We have included the weighting rules and online comparison in Section 4.3, under “Novelty Weighting Ablation” (Eqs. 15–16 and Table 5) of the revised manuscript.
We hope these results clarify your concerns. Thank you again for your thoughtful feedback.
The response of weakness_1 and question_1
Comment: We sincerely thank you for your careful review and thoughtful questions. We greatly appreciate your positive assessment of our motivation, unified framework, and supplementary validation, as well as your detailed comments on recognition-error correlation, response-model accuracy, and geometric weighting. Below are our responses.
Response: Our measurements show more joint false positives at geometrically similar viewpoints, supporting the use of geometric similarity to identify repeated recognition evidence.
We collect 12 views of 424 objects from 10 training scenes: 5,088 images, 848 matching/non-matching object–description pairs, and 10,176 VLM responses.
For each object–description pair, we rank the 66 possible view pairs by geometric similarity:
Kij=exp(−2σp2∥pi−pj∥2−2σθ2θij2),
where pi is the camera position, θij is the viewing-direction difference, σp=6,m, and σθ=45∘. The 22 highest-scoring and 22 lowest-scoring pairs form the similar and dissimilar groups, respectively.
Using manually annotated visibility labels, we retain pairs with the target absent from both images and measure joint false positives:
J=Pr(yi=1,yj=1∣vi=0,vj=0),
where yi=1 denotes a positive VLM response and vi=0 denotes annotated target absence. Each sequence must contain at least two eligible pairs in both groups. Rates are averaged within objects and then equally across objects.
We additionally evaluate a restricted subset requiring non-matching descriptions and equal occlusion and known clutter labels within each pair.
The table below reports joint false-positive rates for similar and dissimilar viewpoints:
Similar views have a 2.14-fold higher joint false-positive rate (30.75% vs. 14.36%); the pattern persists in the restricted subset (9.32% vs. 6.23%), supporting geometric similarity as a cue for repeated recognition evidence.
This measures repeated false positives directly and supports downweighting potentially redundant evidence in Section 3.5.
We have included the view-pair analysis in Appendix A.3, “Geometric Similarity and Evidence Redundancy” (Table 7) of the revised manuscript.