- Rating
- 1(−1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces MoZoo, a video diffusion framework for mesh-guided animal appearance synthesis, generating photorealistic animal videos by combining the motion of an animated mesh with an appearance specified by text, image, or video reference. To address the scarcity of paired training data, the authors build MoZoo-Data, a 62K-clip dataset combining UE5-rendered synthetic pairs and real animal videos processed via inverse mesh generation. The model uses Role-Aware RoPE (RAR-RoPE) for temporal alignment and Asymmetric Decoupled Attention (ADA) for information routing, and is evaluated on a 120-case MoZooBench.
Critical strengths
- The problem of mesh-guided animal appearance synthesis is well-motivated.
- MoZoo-Data and especially the inverse-mesh pipeline that extracts pseudo-pairs from real videos are valuable contributions.
- RAR-RoPE cleanly handles the temporal misalignment between reference and target/mesh tokens, and its ablation shows clear failure modes when removed.
- The model shows impressive cross-species texture transfer and multi-entity handling.
Critical weaknesses
- The model's behavior resembles texture transfer onto a pre-defined mesh video rather than genuine mesh-guided appearance synthesis. It fails to truly decouple motion from appearance; the generated video heavily retains the overall body shape and proportions of the input mesh video. The mesh already determines the full layout, so the network's role reduces to painting textures onto a known proxy, which limits its capability to synthesize vivid video.
- Because the overall body shape is largely determined by the input mesh video, the showcased results are dominated by animals of similar stature. I wonder whether the model can generalize when the reference image is an AIGC-generated sample with unusual appearances rather than a real photo.
- There are many existing models that take a coarse render or layout as the condition. For example, LTX-2.5-22b-IC-LoRA-Layout-To-Render accepts a rough white-model/layout render and synthesizes the final video. I think there should be a comparison.
- The methodological contribution is relatively incremental. ADA is a standard masked attention pattern that decouples condition streams. The RAR-RoPE is also a minor modification .
Questions for authors
-
Have you compared RAR-RoPE against simpler alternatives such as adding explicit modality/role embeddings (e.g., learnable mesh/reference/target tokens) ? Without this, the necessity of the custom RoPE scheme is unclear.
-
The pipeline and data are built around quadruped animals. Can this method and pipeline be extended to non-quadruped categories (e.g., birds, fish, or humans).
9 comments
Response to Reviewer AFjq(part2/2)
w4 Methodological contribution
As reviewers BUyi and No9k recognize, MoZoo addresses a practical problem in controllable animal video generation. Our contribution is a complete pipeline, from training data construction to model design, for rendering mesh-defined animal animations with independently specified appearance.
1. A unified conditioning framework. MoZoo takes a rendered mesh animation and an appearance reference in text, image, or video form, and generates a realistic animal video that follows the mesh-defined geometry and motion while matching the reference appearance. Within this framework, RAR-RoPE encodes the correspondence between synchronized mesh and target frames while accommodating asynchronous references. ADA allows target tokens to access both structural and appearance information while protecting the conditioning streams from feedback from noisy target tokens.
2. A scalable data-construction pipeline and MoZoo-Data. Real animal videos provide diverse appearances but generally lack corresponding mesh animations. We address this bottleneck by training an inverse generation model on paired synthetic renders and applying it to real videos to obtain coarse mesh proxies. MoZoo-Data combines these real-video pseudo-pairs with aligned synthetic renders, providing approximately 62K training clips. This enables training on diverse real animal footage for mesh-guided appearance synthesis without requiring explicit 3D reconstruction of each animal.
Realizing this task requires the data pipeline and conditioning framework to work together. Our same-data comparisons and component ablations support their respective contributions. MoZoo’s contribution therefore extends beyond an individual positional encoding design: it establishes a task formulation and a working data-to-model pipeline for combining frame-aligned structural guidance with independent appearance control.
Q1
We added a comparison with role embeddings. As shown in the table below, the two approaches perform similarly with image references, while RAR-RoPE performs better with video references. Our contribution is to provide a practical framework for mesh-guided animal appearance synthesis, with conditioning modules that can be replaced by or combined with role embeddings or more effective methods in the future. In our evaluation, the full framework substantially outperforms the channel-concatenation and VACE baselines, while RAR-RoPE better preserves appearance details than role embeddings in complex-texture transfer cases.
Table R12. Role embeddings on the expanded real-world test set.
| Method | Video Quality | Paired-Target Fidelity | ||||||
|---|---|---|---|---|---|---|---|---|
| Subject Consist. ↑ | Background Consist. ↑ | Motion Smooth. ↑ | Imaging Qual. ↑ | Aesthetic Qual. ↑ | PSNR ↑ | LPIPS ↓ | SSIM ↑ | |
| Role Embeddings (Image) | 97.76 | 98.64 | 99.32 | 69.27 | 56.31 | 22.11 | 0.078 | 0.912 |
| Role Embeddings (Video) | 97.63 | 99.12 | 99.30 | 69.35 | 56.58 | 22.02 | 0.080 | 0.910 |
| MoZoo (Image) | 97.83 | 98.80 | 99.37 | 69.45 | 56.65 | 22.16 | 0.075 | 0.920 |
| MoZoo (Video) | 97.98 | 98.92 | 99.45 | 69.51 | 56.91 | 22.39 | 0.070 | 0.925 |
Table R13. Role embeddings on the rendered mesh test set.
| Method | Video Quality | Paired-Target Fidelity | ||||||
|---|---|---|---|---|---|---|---|---|
| Subject Consist. ↑ | Background Consist. ↑ | Motion Smooth. ↑ | Imaging Qual. ↑ | Aesthetic Qual. ↑ | PSNR ↑ | LPIPS ↓ | SSIM ↑ | |
| Role Embeddings (Image) | 97.57 | 98.65 | 99.20 | 69.22 | 60.71 | 21.28 | 0.077 | 0.906 |
| Role Embeddings (Video) | 97.59 | 98.85 | 99.26 | 69.34 | 60.83 | 21.17 | 0.079 | 0.908 |
| MoZoo (Image) | 97.66 | 98.82 | 99.24 | 69.36 | 60.98 | 21.34 | 0.074 | 0.913 |
| MoZoo (Video) | 97.86 | 98.94 | 99.33 | 69.40 | 61.02 | 21.54 | 0.069 | 0.920 |
We sincerely thank you for your valuable suggestions, which have helped us refine and strengthen the paper. If you have any additional questions or concerns, please do not hesitate to let us know.
Thank you for your detailed rebuttal and additional experiments. However, i concern with your results.
- The motion following in the video demo_comparison_reference.mp4 (The tiger) is bad could you provide an explanation.
- I still holds that the demo is similar to texture transfer. I admit that the data construction pipeline is valuable in this specific task and domain, but it is not essential in current video generation area. For example, LTX exhibit more photo-realistic results even they do not specifically train on this domain. In contrast, your results are sometimes oversaturated. I think scaling LTX and its data construction pipeline is a more promising future.
Response to Reviewer AFjq(part1/2)
Thank you for your positive evaluation of our work and for the valuable suggestions provided. Below, we address your concerns point-by-point.
W1
We would like to clarify that MoZoo goes beyond texture transfer. Our design follows the workflow of animators, who use mesh videos to define structure and motion before grooming and rendering fur, a process that is often time-consuming and repetitive. MoZoo generates realistic animal videos by adapting fur characteristics from a reference animal to a target mesh, even when their body shapes differ.
W2 & Q2 — Cross-shape, AIGC, and non-quadrupedal examples
We thank the reviewer for the suggestion. We added two sets of examples to evaluate generalization.
Appearance transfer across body shapes and with AIGC references. MoZoo transfers appearance when the reference animal and the input coarse mesh differ in body shape, or when the reference image is AI-generated and depicts an unusual appearance. The results are available here.
Non-quadrupedal animals. We added examples of birds and fish. Our data construction pipeline produced the coarse mesh videos, and MoZoo generated the corresponding output videos. The results are available here.
Our current training data provide limited coverage of non-quadrupedal animals and unusual appearances. We expect that broader coverage would make MoZoo’s results more consistent in these settings.
W3 — Comparison with coarse-render baselines
Thank you for raising this question. We added quantitative and qualitative comparisons with LTX-2.5-22b-IC-LoRA-Layout-To-Render (released on October 1, 2026, after the submission deadline). LTX supports both image and text guidance. Under image guidance, it struggles to preserve the reference appearance throughout the video and shows limited cross-species texture transfer in our evaluation. The video comparisons are available here.
Table R10. LTX comparison on the expanded real-world test set.
Table R11. LTX comparison on the rendered mesh test set.