- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper addresses the practical and challenging task of Aerial-Ground Person Re-Identification (AG-ReID), which involves severe scale, viewpoint, and geometric deformations across aerial and ground camera views. Existing AG-ReID methods primarily focus on 2D representation learning, limiting the mitigation of viewpoint bias in 2D space. To address this limitation, this paper proposes a View-Robust 3D Representation Learning (VR3D) framework that learns representations in a view-robust 3D space. Specifically, it maps image features into 3D human representations and employs View-Robust 3D Representation Interaction (VR3I) to establish interactions between 2D semantics and 3D human representations in a canonical 3D space, along with Reliability-Aware Fusion (RAF), which adaptively aggregates 2D, 3D, and interactive 2D–3D features. The proposed method is evaluated on three AG-ReID datasets to demonstrate its effectiveness.
Critical strengths
- The paper addresses a major limitation of existing AG-ReID methods, viewpoint bias in the 2D feature space learning, through View-Robust 3D Representation Learning.
- The paper's motivation to mitigate the bottleneck of 2D viewpoint bias is well-founded, and addressing this limitation by lifting representations into 3D space is interesting.
Critical weaknesses
- The paper relies on an offline 3D reconstruction pipeline, which limits the practical applicability of the proposed framework in real-world scenarios. The need to reconstruct 3D representations for each image introduces additional computational overhead, limiting the framework's suitability for end-to-end deployment.
- The overall contribution is limited, as the proposed VR3I and RAF modules are based on attention and fusion mechanisms that have been commonly explored in the Re-ID and computer vision literature.
- As the paper's main motivation or objective is to mitigate viewpoint bias, the use of view-specific features for Reliability-Aware Fusion requires stronger justification to demonstrate that these features reduce viewpoint-specific bias.
- The evaluation is limited, as the proposed method should be evaluated on large-scale real-world datasets such as LAGPeR and CP2108, along with cross-dataset evaluations to demonstrate its generalizability.
Questions for authors
- Provide a detailed computational complexity comparison, including key metrics such as FLOPs, trainable parameters, inference speed, and memory usage, against the ViT baseline and VDT method to analyze the practical applicability of the proposed method.
- Clarify the inference settings used during evaluation/testing, including how end-to-end retrieval is performed.
- As the paper's main motivation or objective is to mitigate viewpoint bias, the use of view-specific features for Reliability-Aware Fusion requires stronger justification to demonstrate that these features reduce viewpoint-specific bias.
8 comments
Furthermore, the 3D-GSA ablation in Table 5 shows a substantial performance decrease when geometric priors are removed from the attention computation.
Table 5. Ablation study of interaction strategies in 3D-GSA on AG-ReID.v1. “Coarse” denotes fusion by adding global 2D and 3D features, while “Geometry” and “Semantic” use only geometric bias and semantic correlation, respectively. “Geo. + Sem.” combines both cues in 3D-GSA.
| Variant | Interaction | A→G R1 (%) | A→G mAP (%) | G→A R1 (%) | G→A mAP (%) |
|---|---|---|---|---|---|
| A | Coarse | 86.53 | 78.93 | 86.90 | 81.15 |
| B | Geometry | 87.11 | 79.60 | 88.46 | 82.15 |
| C | Semantic | 86.82 | 79.48 | 87.84 | 81.74 |
| D | Geo. + Sem. | 87.39 | 79.95 | 89.60 | 82.87 |
Moreover, with the rapid advances in 3D reconstruction, we believe that 3D representation learning will become increasingly valuable for addressing identity representation bias caused by extreme viewpoint variations. This research direction also enables aerial-ground person ReID to benefit directly from future advances in 3D reconstruction techniques.
Weaknesses3
As the paper's main motivation or objective is to mitigate viewpoint bias, the use of view-specific features for Reliability-Aware Fusion requires stronger justification to demonstrate that these features reduce viewpoint-specific bias.
R3
We sincerely thank the reviewer for this valuable question. We would like to clarify that introducing view-specific features is not intended to preserve viewpoint bias in the final identity representation. Instead, we leverage the additional visual cues provided by viewpoint information to assist in estimating the reliability of the 2D appearance features, 3D structural features, and their interaction features obtained through our 3D representation learning framework, thereby further enhancing the viewpoint robustness of the final identity representation.
Specifically, our method lifts images from different viewpoints into a shared canonical 3D space, where fine-grained 2D appearance information and 3D structural information are jointly exploited to mitigate viewpoint bias. However, the reliability of the three resulting feature representations varies across different samples. To address this issue, we introduce the Reliability-Aware Fusion (RAF) module. We further observe that different viewing perspectives affect 2D appearance features, 3D structural features, and their interaction features differently, causing their relative reliability to vary with viewpoint and 3D reconstruction quality. For example, under extreme overhead viewpoints, 2D images may lose important identity details, while reliable 3D structural features can still provide discriminative information. Therefore, although viewpoint information is a source of bias that needs to be mitigated in identity matching, it also provides useful visual cues that can assist in estimating the reliability of different feature representations. This observation motivates the introduction of view-specific information into RAF.
In our implementation, view-specific features are used only to construct the Query in the attention mechanism of RAF, providing supplementary information for estimating the relative reliability of the three feature branches. The Keys and Values are constructed from the 2D appearance features, 3D structural features, and their interaction features.
Thus, VR3I and RAF form a complementary and coherent design. VR3I mitigates viewpoint bias through 3D representation learning, while RAF further incorporates viewpoint information as an auxiliary cue to adaptively fuse identity features. Rather than simply removing all viewpoint information, we exploit its useful visual cues to support the learning of more viewpoint-robust identity representations.
Table 6. Ablation study of RAF on AG-ReID.v1. “Average” uses average fusion, “CA” performs cross-attention fusion, and “View” conditions fusion on view-related features.
| Variant | Average | CA | View | A→G R1 (%) | A→G mAP (%) | G→A R1 (%) | G→A mAP (%) |
|---|---|---|---|---|---|---|---|
| A | ✓ | 86.44 | 79.39 | 86.90 | 82.18 | ||
| B | ✓ | 87.01 | 79.54 | 88.46 | 82.15 | ||
| C | ✓ | ✓ | 87.39 | 79.95 | 89.60 | 82.87 |
The ablation results in Table 6 further support this design, showing that incorporating view-specific information helps the model better balance the contributions of the three feature representations, leading to improved retrieval performance. Moreover, the upper-right and lower-right examples in Fig. 7 illustrate that when extreme viewpoint variations degrade 2D appearance features while the reconstructed 3D structures remain reliable, RAF assigns higher fusion weights to the 3D structural branch.
Weaknesses4
The evaluation is limited, as the proposed method should be evaluated on large-scale real-world datasets such as LAGPeR and CP2108, along with cross-dataset evaluations to demonstrate its generalizability.
R4
We sincerely thank the reviewer for this valuable suggestion. To further evaluate the effectiveness and generalization ability of VR3D, we conduct additional experiments on the large-scale real-world LAGPeR and CP2108 datasets following their respective official cross-view retrieval evaluation protocols. We also conduct cross-dataset evaluations following the protocol of the original VDT paper.
(1) Evaluation on LAGPeR
LAGPeR is a large-scale real-world dataset, and we conduct additional experiments following its official evaluation protocols. As shown in the table, VR3D achieves the best performance across all three evaluation protocols. These results further demonstrate the effectiveness of VR3D on large-scale real-world aerial-ground person ReID datasets.
Comparison with existing methods on LAGPeR.
| Method | A→G R1 | A→G mAP | G→A R1 | G→A mAP | G→(A+G) R1 | G→(A+G) mAP | Average R1 | Average mAP |
|---|---|---|---|---|---|---|---|---|
| ViT[a] | 38.67 | 27.25 | 32.04 | 30.69 | 18.88 | 15.31 | 29.86 | 24.42 |
| VDT[b] | 40.15 | 28.97 | 33.55 | 31.98 | 19.50 | 16.45 | 31.07 | 25.80 |
| SeCap[c] | 40.51 | 29.59 | 33.95 | 32.60 | 22.23 | 17.97 | 32.23 | 26.72 |
| SD-ReID[d] | 40.15 | 29.72 | 34.47 | 32.86 | 22.85 | 18.88 | 32.49 | 27.15 |
| ViSA[e] | 40.58 | 30.00 | 34.01 | 32.78 | 22.32 | 18.33 | 32.30 | 27.04 |
| VR3D | 41.66 | 30.58 | 35.65 | 33.69 | 23.21 | 18.89 | 33.51 | 27.72 |
(2) Evaluation on CP2108
CP2108 is a large-scale real-world aerial-ground person ReID dataset, and we conduct additional experiments under cross-view retrieval protocols. As shown in the table, VR3D consistently achieves the best performance across all evaluation metrics. Compared with the strongest baseline, SVPR-ReID, VR3D improves Rank-1 accuracy by 5.28 and 4.67 percentage points under the A→G and G→A protocols, respectively, with corresponding mAP improvements of 2.18 and 2.25 percentage points. These results further demonstrate the effectiveness of VR3D in learning viewpoint-robust identity representations on large-scale real-world aerial-ground person ReID datasets.
Comparison with existing methods on CP2108.
| Method | A→G R1 | A→G mAP | G→A R1 | G→A mAP | Average R1 | Average mAP |
|---|---|---|---|---|---|---|
| VDT[b] | 42.76 | 33.64 | 40.59 | 31.74 | 41.68 | 32.69 |
| SeCap[c] | 63.55 | 46.95 | 63.39 | 46.19 | 63.47 | 46.57 |
| SVPR-ReID[f] | 64.25 | 47.72 | 63.76 | 47.04 | 64.01 | 47.38 |
| VR3D | 69.53 | 49.90 | 68.43 | 49.29 | 68.98 | 49.60 |
(3) Cross-Dataset Generalization
To further evaluate the cross-dataset generalization ability of VR3D, we conduct additional experiments by transferring from CARGO to AG-ReID, following the evaluation protocol reported in Section 7.3, Table 4 of the original VDT paper. As shown in the table, VR3D achieves 29.89% Rank-1 and 18.04% mAP under the A→G protocol, and 20.89% Rank-1 and 15.63% mAP under the G→A protocol. Compared with VDT, VR3D improves these four metrics by 10.56, 6.23, 5.51, and 3.90 percentage points, respectively. The results demonstrate that our proposed viewpoint-robust 3D representation learning also substantially improves cross-dataset generalization ability.
| Method | A→G Rank-1 (%) | A→G mAP (%) | G→A Rank-1 (%) | G→A mAP (%) |
|---|---|---|---|---|
| ViT[a] | 1.59 | 1.95 | 3.01 | 2.31 |
| VDT[b] | 19.33 | 11.81 | 15.38 | 11.73 |
| VR3D | 29.89 | 18.04 | 20.89 | 15.63 |
Weaknesses1
The paper relies on an offline 3D reconstruction pipeline, which limits the practical applicability of the proposed framework in real-world scenarios. The need to reconstruct 3D representations for each image introduces additional computational overhead, limiting the framework's suitability for end-to-end deployment.
R1
We sincerely thank the reviewer for this valuable comment. We would like to clarify that although VR3D employs SAM3/SAM3D for 3D feature extraction, this does not require repeated 3D reconstruction during retrieval. Similar to conventional embedding-based person ReID systems, VR3D performs feature extraction for gallery images only once during offline database construction. After encoding, only the final identity embeddings are retained, and all intermediate 3D features can be discarded. Therefore, online retrieval requires processing only the incoming query image, without reconstructing or re-encoding any gallery images.
Regarding end-to-end deployment, our measurements show that SAM3D reconstruction, the most GPU memory-intensive stage in our pipeline, has a peak memory usage of approximately 13.85 GiB, indicating that the pipeline can run on consumer-grade GPUs. Furthermore, the average intermediate 3D feature size is only 0.197 MB per image, and these features do not require long-term storage, avoiding additional storage overhead. For gallery construction, feature extraction and encoding can also be performed in parallel on cloud servers as a one-time offline process.
Overall, VR3D does not require repeated 3D reconstruction of gallery images during online retrieval. Instead, it incorporates the benefits of 3D structural information into a standard embedding-based retrieval framework. By combining offline gallery construction with flexible query processing, VR3D enables more viewpoint-robust identity representations while supporting practical deployment.
Weaknesses2
The overall contribution is limited, as the proposed VR3I and RAF modules are based on attention and fusion mechanisms that have been commonly explored in the Re-ID and computer vision literature.
R2
We sincerely thank the reviewer for this valuable comment. We would like to clarify that the core innovation of VR3D lies in introducing 3D representation learning into aerial-ground person ReID, providing a new approach to mitigating identity representation bias caused by extreme viewpoint variations. Attention and fusion serve as technical mechanisms to realize this design, rather than constituting our core contributions.
Specifically, existing methods mainly address viewpoint bias through 2D feature disentanglement. In contrast, our VR3I lifts 2D image patches from different viewpoints into a shared canonical 3D space, where geometric priors guide the attention computation to establish spatial associations between fine-grained 2D appearance features and 3D structural features. This enables the model to jointly exploit rich identity details from 2D images and structural information in 3D space, thereby learning more viewpoint-robust identity representations.
Building on this design, we further consider the influence of 3D reconstruction quality and viewing perspectives on feature reliability. Since the reliability of 2D appearance features, 3D structural features, and their interaction features varies across samples, we introduce the Reliability-Aware Fusion (RAF) module to adaptively adjust the fusion weights of these three representations according to sample-specific features. This allows the model to fully exploit their complementary information while reducing the influence of unreliable features on the final identity representation.
The experimental evidence further supports this distinction. The main ablation experiments in Table 4 validate the effectiveness of our core design, which consists of 3D representation learning and reliability-aware fusion for aerial-ground person ReID, rather than the use of attention and fusion operations alone.
Table 4. Ablation study of key components on AG-ReID.v1.“3D Global Feature” directly introduces the global 3D representation f3D, “Fused Feature” denotes the fuse representation ffuse learned by VR3I, and “Multi-Features” denotes average fusion of f2D, ffuse, and f3D. RAF further performs reliability-aware fusion.