- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes Graph Structured Flow Matching (GSFM) for stochastic human motion prediction. The main idea is to formulate the entire future skeletal trajectory as a single object transported by a conditional flow matching process. The authors represent skeletons on a constrained geometric space using root positions and unit bone directions, and design a graph-based velocity network with spatial and temporal attention to model skeletal interactions. Experiments on AMASS and zero-shot transfer to Human3.6M are provided to evaluate prediction accuracy, diversity, and skeletal consistency. The paper aims to combine flow matching, geometric skeleton representation, and graph-structured modeling into a unified framework for physically plausible human motion prediction. However, the overall presentation, logical justification of the proposed approach, and coverage of relevant literature are not sufficiently developed, which makes the contribution and significance of the work less convincing.
Critical strengths
- Conceptually clean formulation of motion prediction using trajectory-level flow matching. The idea of modeling the whole future motion sequence in one shot, rather than generating poses sequentially, is principled and gives a unified probabilistic formulation.
- Geometry-aware skeleton representation. Representing bone directions on spherical manifolds offers an elegant way to preserve bone length constraints without extra post-processing.
Critical weaknesses
Weakness 1: Limited novelty and insufficient justification of the central methodological contribution.
The main contribution of this paper appears to be an integration of several existing techniques, including flow matching, geometric skeleton representations, and graph-based attention mechanisms. While the combination is sound, the paper does not convincingly demonstrate that Graph Structured Flow Matching introduces a substantial conceptual advance beyond existing human motion generation and prediction frameworks.
In particular, the central motivation of using a graph-structured velocity field is not sufficiently validated. The paper does not compare against a strong non-graph flow matching baseline, making it unclear whether the observed improvements are due to the proposed graph formulation, the geometric representation, or other architectural choices. This weakens the claim that the proposed framework provides a fundamentally better approach for motion prediction.
Weakness 2: Unconvincing empirical analysis to support the claimed advantages.
Although the paper reports extensive quantitative results, the experimental evaluation does not adequately analyze the proposed design choices. The reported improvements over previous methods are relatively limited, and the ablation studies mainly focus on removing spatial or temporal attention components rather than isolating the contribution of the key components of the framework.
For example, the paper lacks controlled comparisons between:
- flow matching against diffusion-based alternatives under comparable settings;
- graph-based velocity modeling against standard transformer architectures;
- manifold-based skeleton representations against unconstrained representations.
Furthermore, given that the paper emphasizes generating diverse and physically plausible motions, the qualitative evaluation is limited. More detailed visualization of generated trajectories, covering diversity and failure cases, would better support the main claims.
Questions for authors
-
The main contribution of the paper centers on the graph-structured velocity field trained with flow matching. Could the authors clarify how much of the gain is attributable to the flow matching formulation itself, for example by training the same network under a diffusion objective with comparable settings?
-
The paper does not compare against a non-graph flow matching baseline. Would it be possible to report such a comparison, so that the effect of the proposed graph-based design can be separated from the rest of the framework?
-
The proposed framework combines flow matching with geometric skeleton representations. Can the authors quantify the contribution of the manifold-based representation by comparing it with a Cartesian-coordinate representation under the same architecture?
-
The paper claims advantages in generating diverse and physically plausible motions, but the qualitative results are largely limited to Figure 1. Could the authors provide additional visualizations, including side-by-side comparisons with baselines and representative failure cases?
7 comments
Part 2. response to W2, Q1, Q2 and Q3
To further strengthen the positioning of GSFM with respect to other frameworks, we have trained the following variations:
- A transformer which learns a joint identifier embedding in place of the kinematic tree features (Transformer FM),
- A flow matching model which uses a Cartesian representation of node states without constraints (Cartesian-flow),
- A diffusion model which uses a Cartesian representation of node states without constraints (Cartesian-Vdiff),
- A Euclidean flow matching model which uses a single bone direction normalization after generation to yield joint positions (Euclidean FM).
Each variation is trained over three seeds at ablation scale, evaluated at 20 NFE on each seed, and each metric is averaged across the seeds.
Table 9: ADE and limb stretching for the GSFM model, Cartesian variations, and Euclidean flow matching configuration.
| Configuration | uADE [cm] | ADE | Str. [%] |
|---|---|---|---|
| GSFM-deep | 9.317 ± 0.063 | − | 0.0 |
| Transformer FM | 9.358 ± 0.034 | +0.4% | 0.0 |
| Cartesian-flow | 9.542 ± 0.032 | +2.4% | 9.46 |
| Cartesian-Vdiff | 9.529 ± 0.016 | +2.3% | 7.74 |
| Euclidean FM | 12.380 ± 0.319 | +32.9% | 0.0 |
The results in Table 9 demonstrate that no tested alternative is able to yield GSFM-level performance in prediction accuracy, bone length preservation, and zero-shot transfer. Specifically, Cartesian-flow, Cartesian-Vdiff, and Euclidean FM all sacrifice performance in ADE relative to GSFM. Transformer FM achieves comparable ADE performance to GSFM, but its learned joint embeddings are tied to the representation of the skeleton in AMASS, so it cannot be applied in a zero-shot transfer setting without retraining. Next, we evaluate how much of GSFM's performance gains can be attributed to flow matching itself. To do so, we introduce another variations of a Cartesian diffusion model which use V predict and X predict, respectively. As above, the subsequent results are evaluated at 20 NFE over three seeds at ablation scale.
In addition to the uADE defined in the reply to Reviewer SVkr, Table 10 reports the unified final displacement error (uFDE), the uMAE, and the unified average pairwise distance (uAPD). Let denote the last frame in . Following [2], the uFDE is the analogue of the uADE evaluated only at the final frame,
and it is reported in centimeters. The uMAE is the MAE defined in the reply to Reviewer SVkr, reported in degrees. The uAPD is the unified version of the average pairwise distance (APD) introduced in [2], which measures the diversity of the predictions as the average distance between pairs of distinct samples among the samples generated for the same observation, where the distance between two samples is averaged over the joints as in the uADE, so that a larger uAPD indicates more diverse predictions.
Table 10: Comparison between GSFM across 3 trained seeds and Euclidean flow matching.
| Configuration | uADE [cm] | uFDE [cm] | uMAE [deg] | uAPD [cm] |
|---|---|---|---|---|
| Cartesian-flow | 9.542 ± 0.032 | 10.842 ± 0.084 | 8.33 ± 0.05 | 18.32 |
| Cartesian-Vdiff | 9.529 ± 0.016 | 10.905 ± 0.027 | 7.82 ± 0.10 | 15.26 |
| Cartesian-Xdiff | 9.625 ± 0.004 | 10.942 ± 0.066 | 8.25 ± 0.28 | 15.18 |
| GSFM | 9.317 ± 0.063 | 10.230 ± 0.086 | 7.22 ± 0.11 | 16.01 |
We see that GSFM outperforms the best performing Cartesian method in ADE (2.2% lower), FDE (6.2% lower), and MAE (7.7% lower), at the cost of a slight reduction in APD performance (5.2% higher). Further, GSFM yields perfect reproduction of bone lengths, while every other tested Cartesian variation has nonzero bone length error.
Part 2. continue response to W2, Q1, Q2 and Q3
Lastly, we compare the GSFM-deep model at full scale to a single seed of Cartesian-flow.
Table 11: Comparison between GSFM-deep and Cartesian-diff at full scale.
| Configuration | ADE | FDE | MAE | APDE | CMD | Str. % | Jit. % |
|---|---|---|---|---|---|---|---|
| Cartesian-flow | 0.4768 | 0.5525 | 5.940 | 2.72 | 5.41 | 1.09 | 0.23 |
| GSFM-deep, three seed mean | 0.4768 | 0.5489 | 5.836 | 2.81 | 5.36 | 0.0 | 0.0 |
Table 11 demonstrates that when compared to Cartesian-flow, GSFM achieves equivalent ADE, improved FDE (0.65% lower), and improved MAE (1.78% lower), improved CMD (0.92% lower), while retaining perfect bone length prediction. The cost of achieving bone length preservation through projection is shown in a reply to reviewer EKoq, where we demonstrate that Euclidean FM gives 0.0% Str. and Jit., but has 87% higher ADE than GSFM.
The above graph ablations and comparison to the Cartesian baseline demonstrate that the developed method achieves (i) improved prediction quality, (ii) perfect bone length preservation, and (iii) ability to transfer directly to unseen skeleton data without retraining or retargeting. We reiterate that, relative to SkeletonDiffusion (lowest ADE of all basline methods), GSFM-deep achieves lower ADE across all trained seeds, 4.7% lower MAE, and 53% lower CMD. Further, GSFM-tied achieves comparable performance with only 4.47M parameters, which is 43% fewer parameters than EquiFusion, the smallest comparable model in the baseline set.
Part 1. response to W1
We thank the reviewer for their feedback and suggestions.
We first clarify what the graph structure provides in the developed GSFM model. In GSFM, the kinematic tree (spatial graph) is used to define the state of the model during generation (which, due to the Riemannian framework always yields a valid skeletal configuration), structure the map from model state to joint positions (using forward kinematics), and as node features (tree depth, number of child nodes, end effector flag). The temporal graph structure (links between the same node across temporal frames) enables the model to enforce temporally consistent motion across generation. To clarify how the performance gains can be attributed to the graph structure, we recall Table 3 from the previously submitted manuscript.
Table 8: Change in ADE with respect to the "Full spatial and temporal attention" configuration.
Table 8 precisely identifies the contribution of the graph structure to the predictive capabilities of the GSFM model. Restricting message passing to one hop in either the spatial or temporal dimension slightly increases ADE, and when message passing is eliminated altogether in the temporal domain, the ADE rises by 52.4%.
We further distinguish the contribution of the spatiotemporal graph to GSFM's performance by comparing to a non-graph baseline. We trained a spatio-temporal transformer which learns a joint identifier embedding in the place of the features which are provided by the kinematic tree. We refer to this model as the "Transformer FM" configuration. All other experimental parameters were held constant with respect to the GSFM-deep, ablation-scale model configuration. Transformer FM yields comparable ADE to GSFM-deep (9.358 ± 0.034 vs. 9.317 ± 0.063) on AMASS. However, Transformer FM is a fundamentally limiting approach in that its learned weights are tied to the joint identities in AMASS, and if it is to be used on any other skeleton, the model must be re-trained. In contrast, GSFM allows the same weights to run on skeletons with different kinematic trees with no retraining or retargeting. In the zero-shot transfer domain, GSFM provides more than a 50% improvement in ADE when compare to the best retargeting-based baseline method (0.491 ± 0.035 vs. 1.094).
Further, to better distinguish GSFM from related methods, we will revise the introduction around the two core contributions, move relevant references from Appendix F (Additional Related Work) into the Introduction, and report all additional comparisons and ablations.