ETA-Motion: Efficient Topology-Agnostic Motion Diffusion via Sparse Joint Learning

Seoyoung Hwang; Tae-Kyun Kim

cs.CVOct 28, 2026

ETA-Motion: Efficient Topology-Agnostic Motion Diffusion via Sparse Joint Learning

Authors: Seoyoung Hwang, Tae-Kyun Kim

Organizations: KAIST · Samsung Electronics

Abstract

Topology-agnostic motion generation aims to synthesize motions for diverse characters with arbitrary skeletons. Unlike conventional motion generation, which assumes a fixed skeletal template, this setting must handle diverse joint configurations and inconsistent joint semantics across characters. Existing methods address this challenge through dense full-joint modeling, which incurs substantial computational cost and hinders learning transferable motion patterns across diverse skeletal topologies. We present ETA-Motion, a topology-agnostic motion generation framework based on sparse joint learning. Instead of learning motion from all joints, our method uses a compact subset of joints to reduce redundancy and trains the motion generator on the resulting sparse skeleton. To facilitate correspondence across diverse topologies, we introduce semantic joint embeddings that combine textual and visual cues, together with topology-aware training objectives for preserving skeletal structure. Although ETA-Motion is trained only on sparse skeletal observations, it supports full-skeleton motion generation during inference. Experimental results demonstrate that ETA-Motion outperforms existing topology-agnostic baselines while significantly improving efficiency and generalization to unseen motions and unseen topologies.

Figures & tables

Figure 2: Overview of ETA-Motion. The model is trained on sparse joint subsets but generates motions for full target skeletons at inference time. To enable transferable motion generation across diverse topologies, we combine sparse joint learning, semantic joint embeddings from textual and visual cues, and topology-aware supervision within a spatio-temporal DiT framework.

Figure 3: Visualization of sparse joint skeletons. From the (a) original skeleton, (b) a compact set of joints is retained, and (c) the retained joints are reconnected to form a sparse yet topology-consistent skeleton.

Figure 4: Qualitative comparison with baseline methods. The red boxes highlight representative failure cases of the baselines: topology distortions in AnyTop, including bone stretching and self-collision, and pose errors in Dragon that accumulate from inaccurate joint rotations. In contrast, ETA-Motion preserves a consistent skeletal structure while producing motions aligned with the text.

Method	Efficiency		Seen			Unseen Motion			Unseen Topology
Method	GPU Mem. (MiB) $\downarrow$	Training (h) $\downarrow$	Coverage (%) $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage (%) $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage (%) $\uparrow$	BLV $\downarrow$	CR $\downarrow$
AnyTop	21,180	66.44	54.35	0.0710	0.0035	42.24	0.5423	0.0039	37.68	0.0624	0.0036
AnyTop-G	21,507	67.80	34.67	0.1419	0.0062	24.01	0.1643	0.0063	11.78	0.2392	0.0073
Dragon	17,075	105.34	72.66	0.0000	0.0030	62.13	0.0000	0.0028	66.82	0.0000	0.0043
Ours	2,717	33.86	88.92	0.0012	0.0007	79.63	0.0009	0.0008	70.66	0.0010	0.0014

Table 1: Quantitative comparison on the Seen, Unseen Motion, and Unseen Topology settings, together with training efficiency. AnyTop-G denotes the AnyTop variant trained with the shared global normalization scheme. Best results are highlighted in bold.

Method	Skeleton-Motion Compatibility (%) $\uparrow$	Text-Motion Alignment (%) $\uparrow$
AnyTop	5.8	12.2
Dragon	13.2	12.9
Ours	81.0	74.8

Table 2: User Preference on baseline comparison.

$K$	Efficiency		Coverage (%)			Preference Score (%)
$K$	GPU Mem. (MiB) $\downarrow$	Training (h) $\downarrow$	Seen $\uparrow$	Unseen Motion $\uparrow$	Unseen Topology $\uparrow$	Skeleton Compatibility $\uparrow$	Text Alignment $\uparrow$
5	1,749	16.10	44.16	32.99	30.54	2.0	4.0
10	1,967	16.06	77.80	65.87	52.94	7.1	13.7
20	2,717	16.84	88.60	75.57	65.73	58.1	37.8
50	4,941	19.09	74.06	66.49	53.36	24.3	31.8
full	12,688	27.44	67.46	56.50	42.45	8.6	12.6

Table 3: Efficiency, Coverage and Preference Score under different joint budgets

K

. Best results are highlighted in bold.

Figure 5: Coverage trends under different joint budgets

K

K	Method	Seen $\uparrow$	Unseen Motion $\uparrow$	Unseen Topology $\uparrow$
20	Ours	88.60	75.57	65.73
	w/o visual emb.	82.52	73.15	68.41
	w/o bone loss	77.52	67.50	63.74
Full	Ours	67.46	56.50	42.45
Full	w/ redundant rep.	50.34	48.03	35.29

Table 4: Component ablations on the Seen, Unseen Motion, and Unseen Topology settings in terms of coverage (%). Best results are highlighted in bold.

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Figure S1 : Qualitative comparison under noisy joint labels. With arbitrary joint identifiers, the model trained with the visual joint embedding generates a forward quadrupedal running motion, whereas the model trained without it produces only subtle motion.

Heuristic	Seen			Unseen Motion			Unseen Topology
Heuristic	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$
FPS	88.60	0.0013	0.0009	75.57	0.0009	0.0009	65.73	0.0010	0.0008
Random	86.23	0.0010	0.0010	75.30	0.0007	0.0008	68.55	0.0006	0.0007
Connectivity-aware	80.47	0.0017	0.0009	74.23	0.0010	0.0010	64.64	0.0009	0.0009
Motion-aware	83.02	0.0014	0.0011	73.64	0.0009	0.0011	62.51	0.0008	0.0009

Appendix

Table S1 : Comparison of alternative joint selection heuristics under a joint budget of

K=20

$K$	Seen			Unseen Motion			Unseen Topology
$K$	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$
5	44.16	0.0195	0.0025	32.99	0.0136	0.0023	30.54	0.0127	0.0031
10	77.80	0.0059	0.0016	65.87	0.0038	0.0012	52.94	0.0050	0.0017
20	88.60	0.0013	0.0009	75.57	0.0009	0.0009	65.73	0.0010	0.0008
50	74.06	0.0033	0.0010	66.49	0.0019	0.0008	53.36	0.0018	0.0009
full	67.46	0.0047	0.0015	56.50	0.0035	0.0013	42.45	0.0044	0.0016

Appendix

Table S2 : Full results for the joint budget ablation at 300K training steps. All variants use the proposed position-only motion representation. We report Coverage, BLV, and CR for the Seen, Unseen Motion, and Unseen Topology settings. The row “full” corresponds to the full-joint setting. Best results are highlighted in bold.

K	Method	Seen			Unseen Motion			Unseen Topology
K	Method	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$	Coverage $\uparrow$	BLV $\downarrow$	CR $\downarrow$
20	Ours	88.60	0.0013	0.0009	75.57	0.0009	0.0009	65.73	0.0010	0.0008
	w/o visual emb.	82.52	0.0025	0.0022	73.15	0.0016	0.0022	68.41	0.0022	0.0019
	w/o bone loss	77.52	0.0026	0.0012	67.50	0.0018	0.0012	63.74	0.0021	0.0012
Full	Ours	67.46	0.0047	0.0015	56.50	0.0035	0.0013	42.45	0.0044	0.0016
Full	w/ redundant rep.	50.34	0.1755	0.0041	48.03	0.0560	0.0024	35.29	0.0397	0.0039

Appendix

Table S3 : Component ablations of ETA-Motion at 300K training steps. We report Coverage, BLV, and CR on the Seen, Unseen Motion, and Unseen Topology settings. Best results are highlighted in bold within each block.

Panel of Figure 13 — Figure S2 : Mesh animation results across diverse skeleton topologies. Each subfigure shows the inverse-kinematics-processed joint motion on the left and the resulting character mesh animation on the right.

Motion Diffusion Models

Motion diffusion models generate, edit, reconstruct, and refine articulated movement from text, audio, video, and other conditions.

See all 23 papers

SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology
Jul 2, 2026Yuhao Zhang, Gerard Pons-Moll, Tolga BirdalGenerative Modeling Motion Representation Learning
Imperial College London · University of Tübingen, Tübingen AI Center
TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation
Jun 10, 2026Cheng-Feng Pu, Jia-Peng Zhang, Meng-Hao Guo +2Markerless Motion Capture Motion Retargeting
Zhili College, Tsinghua University, China · BNRist, Department of Computer Science and Technology, Tsinghua University, China · VAST, China
UniMate: One Unified Model to Animate Diverse Skeletons
Sep 4, 2026Linzhan Mou, Jiahui Lei, Zhiyang Dou +4Text-to-Motion Generation Motion Diffusion Models
Princeton University, USA · University of California, Berkeley, USA · Massachusetts Institute of Technology, USA +1

Jul 2, 2026J/K move · Enter open · S save

SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology

Yuhao Zhang, Gerard Pons-Moll, Tolga Birdal

Imperial College London · University of Tübingen, Tübingen AI Center

Generative Modeling Motion Representation Learning

Open paper AskPDF arXiv

Modeling motion for articulated objects of arbitrary skeleton topology remains difficult: existing motion generators target a fixed human skeleton, and prior adaptations either fail to share a vocabulary across rigs or discard motion detail through global pooling. Our key observation is that while joint-level motion does not correspond cleanly across species, motion of functional joint groups does: a human arm, a wolf foreleg, and a bird wing share motion structure despite differing joint counts and connectivity, a correspondence that joint names (e.g., "forearm", "wing_L1") partially expose even when topology does not. We introduce SAMoR (Skeleton-Aware Motion Representation for Articulated Objects), a cross-topology motion representation that encodes each motion segment as a small fixed number (

K=8

) of part tokens shared across arbitrary skeletons. A graph-transformer encoder consumes per-joint motion features, kinematic graph structure, and joint-name embeddings, then compresses them into part-level tokens via cross-attention pooling and residual vector quantization, yielding a discrete motion codebook shared across rigs. To keep the part queries from collapsing into redundant global representations, we introduce a topology-agnostic attention supervision loss, with joint-name dropout to reduce over-reliance on text labels. We curate a heterogeneous corpus from HumanML3D, Truebones Zoo, and animated Objaverse-XL assets, and evaluate SAMoR on held-out characters with unseen skeletons. It supports accurate reconstruction and cross-topology transfer, and enables text-conditioned generation and part-wise editing via a MaskGIT token generator. SAMoR reaches

2.75 \times 10^{-2}

normalized MPJPE on cross-topology reconstruction,

5.8\times

below the strongest adapted variable-

J

tokenizer baseline, while remaining competitive with fixed-skeleton specialists on HumanML3D.

Abstract

Motion Diffusion Models

Explore similar work

SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology

TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation

UniMate: One Unified Model to Animate Diverse Skeletons