- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper focuses on how to automatically recover editable 3D skeletal structures, skinning weights, and corresponding skeletal motions from dynamic 4D meshes reconstructed from monocular videos. The authors propose ZORA, an optimization-based framework that requires no additional training of a rigging model. The core idea is to leverage temporal motion coherence among vertices as a cue for inferring underlying skeletal structures and skinning relationships. First, the authors construct Motion Affinity from vertex trajectories obtained through 4D reconstruction and motion cues extracted from upstream models to identify surface regions exhibiting similar motion patterns. Next, Stretch-Aware Kinematic Scaffold Extraction adjusts graph traversal costs based on the temporal stretching of mesh edges, reducing erroneous connections caused by self-contact or temporary proximity, and constructs an initial skeletal structure through geodesic path search. Finally, Unified-Coherence Rigging Optimization jointly optimizes skinning weights and per-frame rigid bone transformations using LBS, ultimately producing editable 3D assets. Experiments are conducted on AnimalKingdom, ModelsResource, and examples constructed from generated videos. Quantitative comparisons are conducted with MoRig and RASR, and qualitative comparisons are conducted with RigAnything and Puppeteer. The experiments covers reconstruction quality, structural validity and ablation studies.
Critical strengths
ZORA leverages temporal motion coherence among vertices to provide additional cues for joint discovery and part segmentation. Meanwhile, the Stretch-aware scaffold incorporates temporal edge stretching into graph traversal costs, thereby reducing spurious connections caused by self-contact or shortcuts across distinct articulated parts.
The authors evaluate their method on unusual animals and generated characters, covering diverse morphologies and complex topological structures. The experimental results demonstrate advantages in certain skeletal structural validity metrics.
Critical weaknesses
The paper somewhat overclaims its zero-shot, prior-free, and joint skeleton optimization capabilities, while the effectiveness of its core contributions remains insufficiently validated. Although the rigging optimization itself does not require additional training, Section 3.1 explicitly states that the construction of Motion Affinity leverages motion cues extracted from the pretrained PAGE-4D model.
I have concerns about the claimed joint optimization of the skeletal structure. In the overview of Section 3, the authors explicitly state that they jointly optimize the skeleton S, skinning weights W, and per-frame rigid bone transformations. However, in Section 3.2, the skeleton is primarily initialized through the Stretch-Aware Scaffold, while the optimization described in Section 3.3 mainly focuses on skinning weights and bone transformations.
Furthermore, one of the central contributions of this paper is the use of Motion Affinity as a key cue for articulation discovery and skinning optimization. However, its effectiveness is currently supported only by the qualitative ablation in Appendix Figure 11. I believe this evidence is insufficient to independently quantify the contribution of Motion Affinity to the final rig quality.
The experimental results do not sufficiently support the main claims. First, the quantitative results do not demonstrate a consistent advantage of ZORA in overall rigging quality. In Table 1 on AnimalKingdom, ZORA achieves the best performance only on the two structural validity metrics, E_viol and E_cross, while performing substantially worse than RASR on E_LBS, E_norm, and E_coh. Similarly, in Table 2 on ModelsResource, ZORA outperforms MoRig-standard only on E_cross, while falling behind on all other metrics.
I find the ablation study not convincingly verify the necessity of the proposed components. In Table 3, most metrics show only marginal changes, and some ablated variants even outperform the full model on certain metrics.
Questions for authors
Section 3.1 mentions extracting motion cues from PAGE-4D attention, while Equation (1) defines Motion Affinity directly using differences in per-frame vertex displacements. Could the authors clarify the relationship between the pretrained features and the geometric motion affinity, as well as their respective roles in the framework?
Could the authors clarify whether S is actually updated during optimization, including the rest-pose joint positions and skeletal topology? If the skeleton is only constructed during initialization, should the scope of the claimed joint optimization be revised accordingly?
The paper provides quantitative comparisons only with MoRig and RASR, while more recent methods such as RigAnything and Puppeteer are evaluated only qualitatively. Could they provide quantitative comparisons with these state-of-the-art methods under the same datasets and evaluation protocols to better substantiate these claims?
The quantitative ablation study mainly focuses on regularization terms in the optimization process, without independently quantifying the contributions of two components (Motion Affinity and the Stretch-Aware Scaffold). Could the authors provide additional quantitative ablations to evaluate their individual contributions?
I would like to see more direct experimental evidence for the self-contact scenarios explicitly highlighted in the Introduction, such as crossed arms and wings folded tightly against a bird's torso?
2 comments
4. Fitting vs. Structural Trade-Offs (W4) & RigAnything / Puppeteer Comparison (Q3, Revised Table 1)
Our claim centers on structural reliability and OOD/corruption robustness rather than unconstrained least-squares fitting: in Table 1, RASR lowers (0.0111) only by routing 67.5% of bones across empty space ( vs. ZORA 0.2040), while in Table 2, ZORA cuts monocular by 13.6$\times$ (0.0172 vs. 0.2338).
We also added RigAnything (trained on 9,388 rigs) and Puppeteer ( rigs) directly into Table 1 & §4.1 on OOD AnimalKingdom (, frozen rest rigs + shared per-frame rigid pose refitting):
- Training-Prior Projection vs. Discovering Unknown Moving Parts: RigAnything and Puppeteer infer structure solely from memorized training shapes, whereas ZORA discovers unknown moving parts from 4D kinematics. Facing unseen morphologies, Puppeteer omits unfamiliar appendages, collapsing to joints on sequences (bear: 2; snake/fish/squid: 3–4) and , while RigAnything projects ungrounded priors that route
49.3%of bones outside the volume (,+0.29worse than ZORA, 95% CI[0.21, 0.37]on33/42clips). - Metric Trade-Offs vs. Motion Understanding: Articulating full, fine-grained moving parts under strict geodesic locality incurs slightly higher (
0.0586native /0.044refit vs. unmasked 6-DOF fitting0.0252/0.0365) and slightly higher / than Puppeteer's near-rigid 2–4 joint stubs (ZORA beats RigAnything on both). Crucially, ZORA achieves the best surface normal consistency among all supervised baselines (, outperforming Puppeteer's0.4214on34/42clips and RigAnything's0.4478) alongside low volumetric violation (,4.4xbelow RigAnything's0.0471), demonstrating faithful understanding of unknown object motion.
We thank Reviewer
TaGqfor the thorough critique regarding claim precision, optimization scope, ablations, resting self-contacts, and quantitative comparisons with supervised static riggers. All updates are integrated into the revised manuscript.1. Terminology, PAGE-4D vs. Eq. (1), and Fixed Skeleton S (
W1, W2, Q1, Q2)W1, revised Abstract & §1): Following standard usage (analogous to zero-shot segmentation/classification with frozen DINO/CLIP backbones), zero-shot rigging denotes zero rig annotations, zero rigging model training, and zero category skeletal templates. Because Stage 2 extracts general visual-motion cues from frozen PAGE-4D, we replaced "prior-free" with "rig-supervision-free and template-free."Q1, revised §3.1, §3.3, Algorithm 1): Revised §3.1 details the exact two-stage link: multi-view renders pass through frozen PAGE-4D attention layers and back-project onto visible 3D vertices (confidence>τconf) to form normalized cosine-Gram cues Gij, which modulate the geodesically regularized 3D displacement affinity Aij (Eq. 1) and gate sparse local pairs PA (Eq. 7). Meanwhile, scaffold discovery (§3.2) uses only 3D vertex trajectories via temporal edge stretch se (Eq. 2).W2, Q2, revised §3 & Algorithm 1): Agreed. Rest joints J and topology E are extracted once in §3.2 and held strictly fixed during §3.3, which jointly optimizes W and {Gbt}.2. Ablation Analysis of Table 3, Stretch Scaffold, and Motion Affinity (
W3, W5, Q4)W5):w/o L_locshifts modestly because Stage 3 already enforces a hard geodesic support mask (0.25D, Table 7 & Algorithm 1) blocking distant weight bleeding. Dropping spatial coherence (w/o L_mesh) lowers 6-frame ELBS (0.0291→0.0135) only via severe pose overfitting that fragments weights, degrading Enorm (0.0966→0.1293) and Ecoh (0.0273→0.0449).W3, Q4, Appendix E.6 Fig. 10 & Appendix F Figs. 13–14): Without the Stretch Scaffold (Fig. 13,14760), joints drift from hinges or collapse—6-frame ELBS drops (0.02448→0.01953), but GT Joint F1 plunges from0.5000to0.0870(Joint CD:0.0212→0.0766). Without Motion Affinity (Fig. 14(d,e)), fragmented per-vertex weights locally collapse under novel articulation, whereas our affinity prior preserves smooth, cohesive part deformation (further validated on unseen motions in Figs. 11–12, Appendix E.7).3. Direct Self-Contact Validation (
Q5, Appendix E.6 Fig. 10 & Appendix G Tables 5–6)Appendix G, Tables 5–6): Under40%resting self-contact (TN 40%), RASR fuses co-moving parts (Joint F10.322→0.114), whereas ZORA achieves 2.6$\times$ higher Joint F1 (0.301), 34% lower Joint CD (0.062vs.0.094), and 34% lower Animation MPVE (0.030vs.0.046) (and directionally reduces contact-crossing paths from0.89to0.30on real AnimalKingdom self-contact clips).§4.3, Appendix E.6, Fig. 10): Directly testing a bird unfolding tightly folded wings shows that ZORA (α=100) cleanly separates and rigs the wings alongside the beak, claw, and tail; w/o Stretch (α=0) misroutes wing bones via wing-torso contact shortcuts and omits both the beak and claw; RASR collapses joints into an unusable dorsal cluster; and RigAnything & Puppeteer fail to rig the folded wings.