- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies identity-preserving human video generation and argues that conditioning on a single reference image and scoring it with same-reference FaceSim rewards copying rather than identity. It proposes a film/TV corpus of 10K identities with image and video references from disjoint shots. The core idea is ID-RoPE, which repurposes four slow temporal RoPE planes as a Hadamard-coded identity.
Critical strengths
- Identity-preserving, multi-subject human video generation is a valuable task, and the observation that same-reference similarity rewards copying is well motivated. ID-RoPE is a reasonably novel design, which binds tokens to their own references through a parameter-free identity coordinate inside RoPE.
- The pipeline behind Reprise-10K is rigorous and reasonable (cross-episode identity clustering; references taken from shots disjoint from the target, with minimum gaps between them; yaw-balanced, diversity-aware reference selection; background removal to prevent leakage).
Critical weaknesses
- The task formulation and method design are incomplete and not discussed in depth.
- The target-side identity coordinate comes from per-frame character boxes, so ID-RoPE does not appear to support inputs without layout boxes. That is the most common usage setting, and the paper does not explain how the model handles it.
- Multiple references from different contexts carry conflicting priors, such as different hairstyles, outfits and makeup. The paper assumes these cancel out, but it does not examine which attributes the output follows or how a user can control them. This affects controllability.
- The experiments and evaluation are ambiguous, raising concerns about the method's actual effectiveness and the fairness of the comparison.
- The RL reward and the final metrics appear to come from the same source. This is not a fair comparison.
- The test set includes celebrities, and the paper does not state whether these identities appear in the training data.
- The method introduces layout control, yet the test set, the quantitative metrics and the comparisons contain no evaluation of it.
- Implementation details for Wan-14B are missing. While at 1.3B, the gains over same-size baselines are not significant.
- The qualitative evidence and dataset description are insufficient, rasing concerns about reproducibility.
- No video files are provided, and the current visualizations are coarse with errors. The caption claims the example shows two characters of the same gender and similar age, but no such example appears in the figure. And there are no three-character visualizations.
- There are no dataset examples or statistics.
Questions for authors
- Do the 100 test identities overlap with Reprise-10K? What are the results on the celebrity and ordinary-individual subsets separately?
- Where do the per-frame character boxes come from at test time? Which references did each baseline receive? In multi-subject evaluation, how are faces generated by baselines (which have no box input) assigned to characters?
- How does the method handle inputs without reference boxes? How does it handle conflicting information across multiple references?
- Please provide the implementation and training details for Wan-14B.
- Please provide more visual examples (including videos and three-character cases) and dataset details (examples and statistics).
2 comments
4. Wan-14B implementation, training details, and ablation
The 14B model freezes the Wan2.1 DiT backbone and updates a LoRA adapter with rank and scaling . SFT runs on Reprise-10K for 10,000 updates at global batch size 16. Reward-gradient post-training starts from the SFT checkpoint and updates the same adapter for 200 updates at global batch size 8.
Post-training uses AdamW with a learning rate of , a gradient-clipping threshold of 1.0, and a velocity-anchor weight of . RL rollouts use a 20-step Euler solver without classifier-free guidance, and the computation graph is retained only for the final denoising step. The nominal rollout budget is 200 × 8 = 1,600. Targets contain 81 frames at 480 × 832 resolution, reference images are 512 × 512 crops, and reference clips contain 65 frames.
The reward encoder is AdaFace-IR101; identity evaluation uses the AdaFace ViT-Base model provided by CVLFace, pretrained on WebFace4M. Although both use the AdaFace training objective, their backbone architectures and pretrained weights differ, and evaluation does not reuse the reward encoder. We will explicitly distinguish their roles in the revised manuscript.
We additionally report the 14B SFT-only versus Full comparison under the default two-image, two-clip configuration:
| 14B configuration | FaceSim ↑ | CCIS ↑ | MotionSmooth ↑ | Natural ↑ | X-CLIP ↑ |
|---|---|---|---|---|---|
| SFT-only | 0.554 | 0.457 | 0.924 | 3.74 | 0.330 |
| Full (SFT + RL) | 0.589 | 0.508 | 0.964 | 3.92 | 0.347 |
Post-training increases CCIS by 0.051, approximately 11.2% relative to SFT-only, and improves the other four reported metrics. This same-scale comparison directly complements the 14B main results with evidence of the post-training contribution.
5. Additional visual results and dataset statistics
We have prepared an anonymous webpage containing four generated-video examples, each accompanied by its three reference images, and 20 dataset visualizations covering single-character and multi-character samples (one, two, and three characters). For each annotated character in the dataset examples, the webpage provides three reference images and three reference clips alongside the target video. These materials are available at the following anonymous URL:
https://review-visuals-8d3f.pages.dev/
The submitted manuscript already reports dataset statistics in Section 4.1 (page 6) and Appendix B, "Scale and scope" (page 13):
| Dataset property | Already reported in the submitted manuscript |
|---|---|
| Number of identities | 10,000 |
| Reference images per character slot | 3–12 |
| Reference clips per character slot | 3–12 |
| Distinct shots spanned by a reference set | 3–24 |
| Target composition | Single-character clips and co-frame clips with two or three characters |
Figure 4 and Appendix B also describe the data construction pipeline, including cross-episode identity clustering, reference selection, dynamics filtering, and background removal. We will consolidate the existing statistics into a clearly labeled table and ensure that figure captions accurately describe the displayed examples.
Response to Reviewer WzgY
1. Train/test identity overlap and celebrity/ordinary-individual subsets
The 100 test identities were fixed before constructing the training corpus. The test set includes both ordinary individuals and celebrities. During training-data collection, we excluded television series and films featuring the held-out test actors, rather than merely removing identical video clips. After data curation, we additionally performed identity-similarity retrieval and a deduplication check across the training and test character references, finding no duplicate identities. Reprise-10K and the test set therefore use an identity-level split rather than merely a clip- or shot-level split.
The test set is balanced, with 50 celebrity identities and 50 ordinary-individual identities.
2. Test-time boxes, baseline reference inputs, and multi-subject evaluation
Inference does not require user-provided target character bounding boxes or per-frame character trajectories. The boxes exported by the data construction pipeline provide target-reference correspondence guidance during SFT, rather than an additional test-time input.
In Table 1, VACE, Phantom, RefAlign, MAGREF, BindWeave, VINO, and SkyReels-V3 receive one reference image per character and no reference clips. Reprise uses two reference images and two reference clips per character by default. We will explicitly distinguish these reference inputs in the benchmark description and the Table 1 caption.
We additionally report Reprise-14B with one reference image per character and no reference clips:
The single-image configuration exceeds the best baseline mean on four metrics and ties the best MotionSmooth score. This control matches the inference reference budget.
For multi-subject evaluation, we first detect faces in the generated video and extract their identity features. Each detected face is compared with the reference identity representations of all characters and is independently assigned to the character with the highest cosine similarity. This offline evaluation procedure is shared by Reprise and the baselines; it does not use predefined target character boxes or spatial regions and does not impose a one-to-one assignment.
FaceSim uses the conditioning references, whereas CCIS uses cross-context evaluation references of the same identity that are not provided to the generator. We will correct the original wording about the "conditioning region" to describe the actual identity-similarity-based assignment rather than a spatial-region-based assignment.
3. Inputs without reference boxes and conflicting reference information
The supported reference format consists of subject-centered face crops grouped by character. Reference assets are coded whole: every token in a character's reference images and clips shares the identity coordinate s=n. No additional reference-side box annotations are required for this format.
During SFT, target tokens inside the non-overlapping region of character n's box receive s=n; tokens outside all boxes or in overlapping regions receive s=0. At inference, target tokens use the default coordinate s=0 without box-derived per-character assignments. The reference-side ID-RoPE identity encoding remains active. Under the fixed-carrier construction, same-character reference-reference pairs receive the identity bias +βl. The explicit same-identity bonus for target-reference pairs is inactive in this configuration, and target video tokens access the references through the learned content term in attention. We will clarify this stage distinction and the Table 2 ablation configurations.
For conflicting references, the task is to preserve facial identity and facial dynamics across contexts, not to reproduce all reference hairstyles, outfits, and makeup simultaneously. Cross-context pooling concerns context-dependent components in the face-embedding space; it does not mean that conflicting appearance attributes are automatically cancelled at the pixel level. References provide identity and facial-dynamics information, while text prompts specify the generation context and appearance conditions. We do not claim strict, independent control over individual appearance attributes or precise spatial layout. The revised manuscript will make this task boundary explicit.