- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
FlowRig proposes a unified framework for skeleton generation from static meshes and dynamic mesh sequences. A mesh-conditioned flow-matching transformer jointly predicts bone slots across frames, while a temporally pooled graph head predicts shared parent assignments. The framework also incorporates bone-count conditioning, uncertainty-based candidate selection, and masked conditioning for interpolation, forecasting, and backcasting. Training proceeds from static reconstruction to dynamic reconstruction and then partially observed sequence prediction. Validation includes static rigging benchmarks, dynamic reconstruction on a curated TexVerse split, an Objaverse-derived evaluation subset with a RigGS comparison, and ablations of static pretraining and the graph head. The reported results demonstrate improvements in reconstruction accuracy and temporal consistency. Prediction and bone-count control are primarily supported by qualitative examples.
Critical strengths
-
Meaningful reconstruction improvements across several evaluations. In Table 1, Ours reduces Articulation-XL 2.0 J2J from Puppeteer's 0.0311 to 0.0264, approximately a 15.1% improvement, without uncertainty-based best-of-five selection. In Table 2, at a 24-frame window, B2B-W decreases from 0.0119 for the fine-tuned Puppeteer baseline to 0.0093. Appendix D further includes a per-sequence optimization baseline on a shared 193-instance evaluation subset: Ours* obtains macro J2J of 0.0513 versus 0.0636 for RigGS. These results give the work substantive empirical value beyond its qualitative demonstrations.
-
A useful unified formulation supported by evidence for static-to-dynamic transfer. Jointly predicting skeletons across time addresses an important limitation of applying static riggers independently to each frame. The same representation accommodates static inputs and partially observed sequences, making the framework potentially useful for animation workflows. Table 3 provides direct evidence for the benefit of static pretraining: dynamic J2J-W improves from 0.0213 to 0.0142. This is consequential given the limited availability of paired dynamic mesh-skeleton supervision.
Critical weaknesses
The distinct benefits of the unified framework are insufficiently established. RigMo already supports rig inference from mesh sequences and masked-frame motion generation, while AniGen combines flow matching with joint-density conditioning and CFG. FlowRig's explicit bone-slot representation and unified tasks may add value, but the evidence mainly establishes reconstruction gains: prediction and count control remain largely qualitative, and Table 3 demonstrates the benefit of static pretraining rather than the specific three-stage curriculum. This leaves the contribution beyond closely related work unclear.
Questions for authors
-
Contribution: What distinct benefits does FlowRig provide beyond RigMo and AniGen, and which ablations isolate the value of its unified formulation and three-stage curriculum?
-
Validation: Can you report missing-frame prediction errors against simple interpolation/extrapolation baselines, together with exact bone-count success rates?
5 comments
[W1, Q1] Benefits over RigMo and AniGen, and ablations [Part 2/2]
(2) Ablations of the curriculum and of the unified formulation. In the paper, Table 3 isolates static pretraining, the step that transfers the geometric prior from large static data to the limited 4D data. As suggested, Tables C2a and C2b now isolate each stage, each evaluated on the capability it adds: Stage 1 on static rigging, Stage 2 on consistent 4D reconstruction, Stage 3 on predicting unobserved frames.
Table C2a: Curriculum ablation under full observation, TexVerse test set (T=24). IDret as defined in Appendix I. FlowRig rows use slots as identity; the frame-by-frame row links bones across frames by Hungarian matching. Lower is better, except IDret.
| training | J2J-W | BDD | IDret (%) bones / fingers |
|---|---|---|---|
| Stage 1 only (static model), frame by frame | 0.0276 | 0.0104 | 80.9 / 57.4 |
| Stage 2 only (no Stage 1) | 0.0213 | 0.0052 | 99.3 / 85.2 |
| Stage 1 -> 2 (Table 2 model) | 0.0142 | 0.0041 | 99.8 / 95.8 |
Table C2b: Curriculum ablation for prediction: J2J on the unobserved frames, TexVerse test set (T=24). Interp. 1/k: every k-th frame observed; forecast / backcast: the first / last half of the clip observed. Zero-shot: masks applied at test time to a model never trained with masks. Lower is better.
| training | J2J: interp. 1/2 | J2J: interp. 1/4 | J2J: interp. 1/8 | J2J: forecast | J2J: backcast |
|---|---|---|---|---|---|
| Stage 2 only (no Stage 1), zero-shot | 0.0318 | 0.0434 | 0.0517 | 0.0504 | 0.0487 |
| Stage 1 -> 2 (Table 2 model), zero-shot | 0.0316 | 0.0434 | 0.0498 | 0.0474 | 0.0454 |
| Stage 1 -> 2 -> 3 | 0.0193 | 0.0233 | 0.0368 | 0.0385 | 0.0373 |
Each stage adds one capability.
- Stage 1 gives the geometric prior. Without it, the 4D model's J2J-W is 50% higher, as shown in Table C2a.
- Stage 2 gives a consistent 4D skeleton. Without it, the bone length (BDD) drifts and identity (IDret) is not well learned, as shown in Table C2a. Additionally, skeleton generation conditioned on a full motion sequence improves the rigging of a single frame as seen in Tables A1 and A2 under the reply to pXUc.
- Stage 3 gives prediction. With masked training, Stage 3 lowers the error in interpolation, forecasting and backcasting tasks, as shown in Table C2b.
We are happy to discuss any further questions on these comparisons or ablations.
[A] Zhang et al. RigMo: Unifying Rig and Motion Learning for Generative Animation. arXiv:2601.06378, 2026.
[B] Huang et al. AniGen: Unified S^3 Fields for Animatable 3D Asset Generation. arXiv:2604.08746, 2026.
[Q2] Prediction baselines and exact bone-count success rates
We appreciate your question and valuable suggestions! As suggested, we report both.
(1) Prediction. We compare with the standard naive baseline of motion in-betweening, interpolation [C], applied to the strongest baseline of Table 2: Puppeteer-D* rigs every observed frame, and the unobserved frames are filled by interpolating between the two nearest keyframes (constant-velocity extrapolation for forecasting and backcasting).
Table C3: Skeleton error on unobserved frames (4D prediction), TexVerse test set; the same as Table A5 in our reply to Reviewer pXUc. J2J-P / B2B-P; lower is better. Interp. 1/k: every k-th frame of a T=24 clip observed; forecast / backcast: the first / last 4 frames of a T=8 clip observed. "w/o Stage 3": the same model before masked training.
| setting | Puppeteer-D* + interpolation: J2J-P / B2B-P | FlowRig w/o Stage 3: J2J-P / B2B-P | FlowRig: J2J-P / B2B-P |
|---|---|---|---|
| Interp. 1/2 | 0.0200 / 0.0146 | 0.0307 / 0.0239 | 0.0181 / 0.0125 |
| Interp. 1/4 | 0.0253 / 0.0188 | 0.0426 / 0.0324 | 0.0220 / 0.0157 |
| Interp. 1/8 | 0.0370 / 0.0284 | 0.0491 / 0.0372 | 0.0357 / 0.0267 |
| Forecast | 0.0374 / 0.0286 | 0.0461 / 0.0344 | 0.0365 / 0.0272 |
| Backcast | 0.0368 / 0.0286 | 0.0441 / 0.0335 | 0.0349 / 0.0263 |
FlowRig is the most accurate predictor in every setting compared with Puppeteer-D* and the same model before masked training.
(2) Exact bone-count success. We report how often the generated skeleton has exactly the requested number of bones, with the ground-truth count as target.
Table C4: Bone-count control accuracy, on Articulation-XL2.0 (AX) / ModelsResource (MR) / Diverse-Pose (DP). Target: the ground-truth count.
| CFG scale s | exact (%) AX / MR / DP | within ±1 bones (%) | within ±2 bones (%) | MAE (bones) |
|---|---|---|---|---|
| 1 | 91.5 / 87.1 / 95.0 | 95.0 / 95.2 / 97.6 | 96.5 / 98.1 / 98.9 | 0.35 / 0.23 / 0.12 |
| 3 | 93.5 / 87.4 / 95.9 | 96.8 / 96.4 / 98.1 | 98.3 / 99.1 / 99.6 | 0.17 / 0.17 / 0.07 |
| 5 | 90.9 / 83.1 / 93.3 | 96.0 / 95.3 / 97.2 | 98.2 / 99.0 / 99.0 | 0.20 / 0.23 / 0.11 |
At these common guidance scales, 83% to 95% of skeletons have exactly the ground-truth count on the three test sets and at least 95% are within one bone. In comparison, AniGen controls the joint count indirectly, through a density condition with five coarse levels [B].
We hope these results answer the question, and we are open to further discussion.
[B] Huang et al. AniGen: Unified S^3 Fields for Animatable 3D Asset Generation. arXiv:2604.08746, 2026.
[C] Harvey et al. Robust Motion In-betweening. ACM TOG 39(4), 2020.
Thanks so much for your insightful questions and valuable feedback! We address each of them in detail below. Also, the updated supplementary video includes new animations and in-the-wild results, and we sincerely hope the reviewer could take a look.
[W1, Q1] Benefits over RigMo and AniGen, and ablations [Part 1/2]
We are grateful for your insightful question and helpful feedback.
(1) Distinct benefits over RigMo and AniGen. The three methods address different problems: RigMo [A] discovers a rig from the deformation of a mesh sequence without rig labels, AniGen [B] generates a new animatable asset from an image, and FlowRig rigs a given mesh or mesh sequence with an artist-style skeleton. Table C1 lists which capabilities each method supports.
Table C1: Capability comparison of FlowRig, RigMo and AniGen.
FlowRig is the only one of the three that supports every row. The main differences: