- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper introduces Generative Video Anonymization (GVA), which aims to suppress whole body identity in videos while preserving action, scene context and realism.
The authors argue that general video editing models fail at this task and propose MOSAIC, a training free pipeline that combines multimodal grounding, counterfactual identity prompts and mask constrained inpainting with a pretrained diffusion transformer. The authors also introduce an egocentric museum dataset and a privacy–utility evaluation protocol.
Experiments on OpenHumanVid and the museum dataset show that MOSAIC achieves the lowest OSNet leakage among the evaluated generative methods, with metric dependent utility.
Critical strengths
-
The paper addresses an important and timely problem: face only anonymization leaves body appearance exposed to person retrieval models.
-
The proposed method is training free, and querying the multimodal model once per track is a practical way to separate visitors from artworks in long egocentric videos.
-
The ablation shows that the counterfactual prompt matters: removing it raises Rank-1 on the museum data from 41.24% to 68.40%.
Critical weaknesses
-
The privacy evaluation does not support the whole body claim. The retrieval protocol is underspecified (lines 613–614): the number of identities, gallery size, cropping and chance level are not given, and Mask Out still reaches 20.23% Rank-1 on the museum data. MOSAIC inpaints inside the original mask and keeps the motion, so silhouette and gait survive by design, yet the only attacker is OSNet, an appearance model. A gait or clothes changing attacker is needed.
-
The utility evidence is weak. TWE is 0.00 for the original video, which Eq. (9) cannot produce, and on the museum data Acons is 82.95 for Mask Out against 84.87 for MOSAIC. On OpenHumanVid, Gaussian blur beats MOSAIC on five of six metrics, and MOSAIC has the highest TWE (17.54). No realism metric is reported.
-
Reproducibility and ablation. The backbone and multimodal model are not identified (three LMMs are cited, line 208), the detector and tracker appear only as "YOLO" and "SAM" in Fig. 2, and no versions, thresholds or prompt templates are given. Table 3 does not define the ablated variants, removing Stage I improves privacy, and no variance or number of runs is reported. Novelty is modest; ReGenHuman (arXiv 2606.14972) should be discussed.
-
The comparison does not isolate the contribution of the counterfactual prompt. The two generative baselines, described as task matched (line 353), do not share MOSAIC's backbone: DeepPrivacy2 works frame by frame (line 458) and UniVideo is a general editor.
Moreover, Stages I and II share a single LMM call (line 197), so removing Stage II may also change the grounding input. A baseline with the same backbone and masks but a generic caption is needed to show that the attribute opposition, rather than any appearance changing prompt, drives the privacy gain.
Questions for authors
-
Could the authors specify how the gallery is built (number of identities, queries, crops, chance level), and explain why Mask Out keeps 20.23% Rank-1 on the museum data?
-
How does MOSAIC perform against a gait or silhouette based attacker evaluated on the same clips?
-
Which models and settings are used, and what does each ablation row in Table 3 run in place of the removed stage?
-
What is OSNet Rank-1 when the gallery is drawn from a different clip of the same person?
2 comments
Isolating the counterfactual prompt (W4)
The Table 3 control fixes masks, generator and sampling settings (68.40% vs 41.24% Rank-1), isolating counterfactual prompt construction.
Novelty and ReGenHuman (W3)
ReGenHuman (arXiv 2606.14972) is concurrent work; we ran its official code (Wan2.1-VACE-1.3B + released LoRA, SAM3 masks) under our protocol.
| Dataset | Method | R-1 | SPS | TWE | |
|---|---|---|---|---|---|
| Belvedere | ReGenHuman | 61.87 | 0.768 | 355.73 | 84.64 |
| Belvedere | MOSAIC | 41.24 | 0.815 | 183.35 | 84.87 |
| OHV | ReGenHuman | 75.35 | 0.879 | 55.22 | 72.28 |
| OHV | MOSAIC | 59.96 | 0.878 | 17.54 | 73.32 |
On the challenging museum data, ReGenHuman shows higher identity leakage under all appearance attackers and higher TWE. Qualitatively, regenerated visitors often retain source clothing colours, hairstyle and accessories (e.g. glasses), while depicted people may also be edited. We will add these examples to the appendix and cite and discuss ReGenHuman.
We see MOSAIC's contribution in grounding real visitors versus depicted humans, in the Re-ID-aware counterfactual prompt, and in the Belvedere benchmark.
Different clip of the same person (Q4)
This requires cross-clip identity labels, which neither dataset has; we list it as a limitation.
Ethics
The study had university ethics approval; camera wearers gave written consent, and museum visitors were notified by exhibition signage. We will provide the committee details in the camera-ready version. The masks and masked videos described in Sec. 4.1 are the intended release; release remains subject to museum approval and a specified access policy, and synchronized gaze data are not part of the current release. We will clarify this and add an Ethics Statement.
We thank the reviewer for the thorough review.
Gallery, chance level, Mask Out (Q1)
Evaluation uses the complete splits: 49 Belvedere clips and 256 OHV clips. A clip may contain multiple people; each detected person track is treated as a pseudo-identity. Because neither dataset provides cross-clip identity labels, tracks cannot be linked across clips. After a fixed shuffle (seed 42), the gallery contains anonymized person crops for all tracks and the queries contain the corresponding original crops. All methods use the same YOLOv8n person-crop protocol (confidence 0.5); random Rank-1 chance is the inverse of the number of gallery identities. The gallery includes observations from the same track without excluding temporally corresponding or adjacent content. Sec. 4.2 and Appendix A state the query/gallery direction backwards; we will correct them.
Mask Out retains 20.23% because detected box crops still contain clip-specific background and mask shape.
Gait or clothes-changing attacker (W1, Q2)
We added GaitBase (OpenGait, CASIA-B), CSCI (EVA-02-L, PRCC; CAL has no released weights) and TransReID (ViT-B/16 + JPM, Market-1501).
<sub>Rank-1 (%); all methods are evaluated on the complete benchmark splits under the same protocol.</sub>
Under CSCI, MOSAIC reduces identity leakage on Belvedere to 22.89 Rank-1 (vs 62.24 DeepPrivacy2 and 58.26 ReGenHuman); on OHV, DeepPrivacy2 is lower under TransReID and CSCI, with lower Acons (48.78 vs 73.32). MOSAIC has the lowest gait Rank-1 among the generative methods (60.00% Belvedere; 66.67% OHV), but both remain far above chance. We will therefore remove the "disjoint feature spaces" claim, limit the demonstrated scope to appearance-based whole-body identity, and leave gait anonymization as future work.
Utility (W2)
Models, settings, templates (W3, Q3)
Stage III uses frozen Wan2.1-VACE-1.3B (81 frames, 480p, 50 UniPC steps, CFG 5.0, shift 16, seed 2025), and Stages I–II use Qwen2-VL-2B-Instruct. The grounding module combines SAM3 proposals, global–local multimodal verification and temporally completed masks; the planning module reasons over four keyframes. Evaluation uses YOLOv8n at confidence 0.5.
The prompts instantiate Secs. 3.1–3.2. Stage I asks the LMM to determine whether the highlighted subject is a real person, artwork or shadow using both the full scene and local crop. Stage II separates identity attributes from action/scene semantics and instructs: "Rewrite the description with the counterfactual person while keeping the action and scene exactly unchanged." For example, "a young woman in a red jacket walking through a museum" becomes "an elderly man in a dark jacket walking through the same museum." Complete templates and category sets will be added to the appendix.
Ablations (W3, Q3)
w/o Stage III keeps the generator, masks and sampling settings fixed but feeds the raw video instead of the identity-erased masked video as visual conditioning. As reported in Table 3, TWE rises from 183.35 to 402.15 and Acons drops from 84.87 to 72.40.
Removing Stage I lowers Rank-1 slightly because every person-like region, artworks included, is regenerated, but SPS drops to 0.542. All results are single runs (seed 2025).