TopX: Text-to-Motion for Unseen Skeletons from the Skeleton File Alone

Tengjiao Sun; Pengcheng Fang; Xiaoyu Zhan; Dongjie Fu; Xiaohao Cai; Hansung Kim

cs.CVOct 25, 2026

TopX: Text-to-Motion for Unseen Skeletons from the Skeleton File Alone

Authors: Tengjiao Sun, Pengcheng Fang, Xiaoyu Zhan, Dongjie Fu, Xiaohao Cai, Hansung Kim

Organizations: University of Southampton · MOGO AI · Nanjing University

Abstract

Text-to-motion models generate for the skeletons they were trained on, while a new character arrives as a skeleton file and nothing else. We study text-to-motion for skeletons that no training clip has used, with no clips of the character, no template, no retargeting and no fine-tuning. We present TopX, a 73M-parameter flow-matching transformer that generates joint rotations and a root trajectory for any kinematic tree from its tree, rest pose and joint names. Motion is normalised by the rest pose and the size of the skeleton, and the rest pose enters as a world-frame descriptor that does not depend on how the rig's author oriented each joint, with rest conventions randomised in training. Attention is factorised over the joints and the frames of a motion and carries a spatial--temporal encoding designed for skeleton graphs of any topology: queries and keys are rotated across joints by a heat-kernel coordinate of the skeleton graph, which is defined for every tree and does not change with the order of its joints or the eigenbasis of its Laplacian, and across frames by a rotary encoding of frame order. To measure what this buys, we build SkelShift: four motion corpora under one codec, 143,334 captioned clips on skeletons of 4 to 142 joints, from which 4,232 clips on 2,043 skeletons are held out by clip, rig, tree class or species and organised along topology, joint count, body plan, species and rig source, and scored by motion quality: Fréchet distances on public kinetic features and on kinematic descriptors, foot skating and ground contact. Against UniMate trained on the same clips, on test rigs without a training clip, TopX lowers the descriptor FID from 5.73 to 4.58 when UniMate's guidance is tuned for the kinetic FID, and the kinetic FID from 1.48 to 0.55 when it is tuned for the descriptor FID, also on motions no training skeleton performs; fewer of its frames sink below the ground.

Figures & tables

Figure 1: TopX. ❶ An unseen skeleton needs no clip: its tree, rest pose and joint names give each joint a feature $e_{j}$ (an MLP of tree and rest-pose features plus the LLM2Vec embedding of the joint’s description), and the motion tokens, one per joint and frame (position, rotation relative to the rest pose, velocity and contact; ground track and heading on the root), are normalised by the rest pose and the skeleton’s size ( Eq. 1 ), so the rest frame is zero. ❷ Each of ten blocks attends over time with queries and keys rotated by $\theta_{f}=f\omega$ , and over the joints with them rotated by $\theta_{j}$ , an MLP of joint $j$ ’s heat-kernel signature at eight scales on the tree, and biased by tree hops; mesh colours show the first principal component of the log signature, on one scale for all skeletons. Caption and flow time $t$ act through AdaLN; sampling from noise generates the motion on Stego, a Truebones test skeleton. Meshes are for display only; the human is SMPL+H [ 37 ] .

Bucket	Source	Unseen at test time	Clips dev / test	Rigs	Trees	Joints	TED	Reused motion
ID-clip	UniML3D	clips of training rigs	70 / 172	135	79	10–60	0	26%
ID-tree	UniML3D	rigs whose tree is seen	255 / 508	759	140	6–60	0	63%
OOD-tree	UniML3D	tree classes (bipeds, quadrupeds)	213 / 320	333	266	11–60	2	15%
OOD-plan	UniML3D	tree classes of rare body plans	40 / 62	70	63	5–60	5	2%
OOD-J $>$ 60 (Mixamo)	UniML3D	rigs of one 65-joint humanoid tree	155 / 350	250	1	65	5	51%
OOD-J $>$ 60 (other)	UniML3D	rigs above the corpus’s joint range	166 / 512	464	184	61–117	7	33%

Table 1: SkelShift buckets. A bucket holds out units —clips, rigs, classes of isomorphic trees or species—and every clip of a held-out unit is removed from training and validation. TED: median tree edit distance from a clip’s tree to the nearest training tree. Reused motion: share of clips whose source animation appears in training (UniML3D: motion fingerprints; game species: the same animation, matched by joint rotations).

			UniMate tuned on FID kin						UniMate tuned on FID desc
			FID desc $\downarrow$		FID kin $\downarrow$		Pen. $\downarrow$		FID desc $\downarrow$		FID kin $\downarrow$		Pen. $\downarrow$
Test clips	Clips	R–R	Ours	Uni.	Ours	Uni.	Ours	Uni.	Ours	Uni.	Ours	Uni.	Ours	Uni.
All	1,062	0.48	4.83	6.06	2.00	2.05	0.24	0.33	4.83	4.32	2.00	2.52	0.24	0.28
ID-clip	172	2.83	7.18	9.09	2.40	2.49	0.25	0.34	7.18	5.96	2.40	2.57	0.25	0.27
No training clip	890	0.55	4.58	5.73	0.55	0.48	0.24	0.33	4.58	4.22	0.55	1.48	0.24	0.28
novel motion	453	1.13	9.63	10.70	1.15	0.89	0.27	0.35	9.63	7.95	1.15	2.17	0.27	0.29

Table 2: TopX against UniMate, both trained on the same 5,023 UniML3D clips (test clips of the four UniML3D buckets, first 60 frames, five seeds; additional metrics: appendix), with UniMate’s guidance tuned on dev by FID kin (left) or by FID desc (right). Bold: lower within a half, the paired 95% interval over rigs excluding zero. R–R: FID desc between two halves of the real clips. Pen.: frames below the ground (real 0).

Figure 2: Samples on unseen test skeletons, each drawn on the rig’s own mesh: five frames at equal times, light to dark. (a) The pair of Tab. 2 , UniMate tuned on FID kin , on four rigs neither model was trained on, ours above UniMate, over at most 60 frames, UniMate’s length. (b) The main model on two held-out game species, a capybara and an emu on their production meshes; the camera follows the animal, and squares show its root path from above. Drawing, more examples and mesh credits: Appendix J .

Bucket	Rigs / clips	KID desc $\downarrow$ (real–real)	Slip $\rightarrow$ (real)	Pen. $\downarrow$	Float $\rightarrow$ (real)	Speed $\rightarrow$
ID-clip	93 / 172	0.950 (0.455)	0.309 (0.353)	0.204	0.110 (0.128)	0.87
ID-tree	504 / 508	0.145 (0.002)	0.304 (0.349)	0.172	0.021 (0.039)	0.90
OOD-tree	218 / 320	1.74 (0.142)	0.310 (0.366)	0.200	0.045 (0.078)	0.77
OOD-plan	45 / 62	10.9 (6.04)	0.176 (0.280)	0.251	0.106 (0.164)	0.81
OOD-J $>$ 60 (Mixamo)	172 / 350	0.664 (0.874)	0.311 (0.363)	0.131	0.024 (0.050)	0.82
OOD-J $>$ 60 (other)	351 / 512	0.240 (0.092)	0.275 (0.333)	0.162	0.021 (0.029)	0.77

Table 3: TopX on every test bucket at full length (up to 240 frames, five seeds per clip), real-clip values in parentheses (

\rightarrow

: closer is better), KID desc next to its real–real value. ∗ Fewer than 20 rigs. The one OOD-J

<

5 test clip enters only the last row.

Arm	OOD- tree	OOD- plan	New species	OOD- rig	Rest $\downarrow$
Real	0.142	6.04	104	0.914	–
Full recipe	1.78	11.1	82.4	1.01	0.44
Learned frame table	1.88	11.7	84.4	1.59	–
Learned joint table	1.87	11.5	83.7	1.12	–
Eigenvectors + SignNet	1.83	11.5	83.6	1.17	–
$-$ augmentation	1.95	12.1	91.8	1.03	0.89

Table 4: Ablations, trained for half the main model’s steps, on the OOD test buckets the changed components are meant for: KID desc on unseen topologies (OOD-tree), rare body plans (OOD-plan), new species and Truebones rigs (OOD-rig), five seeds per clip, up to 240 frames. Rest: median change of the output, in mean bone lengths, when a test rig’s rest convention is turned ( Appendix I ). Real: KID desc between two halves of the real clips. Half-widths: Appendix I .

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Slice	Content	Rows
0:3	position: XZ from the smoothed root track, Y absolute	all
3:9	rotation $\mathbf{R}_{j}\mathbf{R}^{\mathrm{rest}\top}_{j}$ , continuous 6D	all
9:12	world velocity (supervision only)	all
12	contact: height $\leq 0.05\,s$ , speed $\leq 0.25\,s$ /s	all
13:15	smoothed root track XZ	root
15:17	heading $(\cos\phi,\sin\phi)$	root

Appendix

Table 5: Channels per joint and frame. Channels 13–16 exist on the root row only. Positions, velocities and the ground track are in the skeleton’s units;

s

is the diagonal of the rest pose’s bounding box.

Width $D$ , blocks $N_{b}$ , heads	512, 10, 8 (73.3M parameters)
Frames	1 rest frame + $L{=}240$ target frames
Heat-kernel scales	$t_{i}=2^{i-2}$ , $i=0,\dots,7$
Temporal rotary base	700
Caption dropout	0.1
Epochs, draws per epoch	600, 55,984 (437 steps of 128; the last 48 dropped)
Optimiser	AdamW, weight decay 0.01

Appendix

Table 6: Settings of TopX.

Bucket	T0	T1	T2a	T2b
ID-clip, ID-tree	1,005	–	–	–
OOD-tree	–	169	145	219
OOD-plan	–	8	32	62
OOD-J $>$ 60 (Mixamo)	–	505	–	–
OOD-J $>$ 60 (other)	–	356	120	202
OOD-J $<$ 5	–	1	–	1

Appendix

Table 7: Topology tiers per bucket (clips, dev and test).

	FID desc $\downarrow$	Skate $\downarrow$	Slide $\downarrow$	Cov. $\rightarrow$	Pen. $\downarrow$	Float $\rightarrow$	Speed $\rightarrow$	KID desc $\downarrow$
Real clips	–	0.254	1.71	0.442	0.000	0.050	1	0.091
$w{=}1.5$	1.88	0.231	1.60	0.452	0.179	0.025	0.78	0.149
$w{=}2$	1.71	0.243	1.74	0.441	0.170	0.030	0.84	0.142
$w{=}3$	1.79	0.260	2.02	0.417	0.172	0.039	0.95	0.176

Appendix

Table 8: TopX on all dev buckets (638 rigs, 1,563 clips, full length, five seeds per clip, 50 Euler steps) at three guidance scales. The real-clip row gives the real values and, under KID desc , the real–real value.

	Evaluations	Seconds
TopX, 20 steps	40	0.67
TopX, 50 steps	100	1.63
TopX, 100 steps	200	3.23
TopX, 200 steps	400	6.43
TopX, 400 steps	800	12.82
UniMate, guidance 3	366.4	6.13

Appendix

Table 9: Network evaluations and seconds per sample on one H200 NVL (50 dev clips, seed 7, batch 1; TopX: the model of Tab. 2 , at the clip’s length). Under guidance every Euler step, and every function evaluation of UniMate’s solver, takes two network evaluations.

		FID desc			FID kin , Motion2Motion		FID kin , Bailando
Test clips	Clips	Ours	UniMate	R–R	Ours	UniMate	Ours	UniMate
All	1,062	4.83	6.06	0.48	2.00	2.05	1.85	1.90
ID-clip	172	7.18	9.09	2.83	2.40	2.49	2.10	2.14
No training clip	890	4.58	5.73	0.55	0.55	0.48	0.56	0.44
novel motion	453	9.63	10.70	1.13	1.15	0.89	1.05	0.77
reused motion	437	0.65	1.64	0.60	0.06	0.24	0.08	0.27

Appendix

Table 10: Same-data comparison, Fréchet distances (test, first 60 frames, five seeds; mean over seeds). Ours: 200 Euler steps at guidance 2, at the clip’s length; UniMate: guidance 7. FID kin on the Motion2Motion and the Bailando release of the kinetic features. Bold: lower than UniMate (our columns) or than Ours (UniMate’s column), the paired 95% interval over rigs excluding zero. R–R: real clips, half against half (groups of at least 100 clips).

	Pen. $\downarrow$		Skate			Cov.			Speed
Test clips	Ours	UniMate	Ours	UniMate	Real	Ours	UniMate	Real	Ours	UniMate
All	0.24	0.33	0.33	0.35	0.35	0.60	0.58	0.64	0.93	1.08
ID-clip	0.25	0.34	0.34	0.37	0.33	0.52	0.51	0.55	0.98	1.23
No training clip	0.24	0.33	0.33	0.34	0.35	0.61	0.59	0.66	0.92	1.06
novel motion	0.27	0.35	0.26	0.33	0.30	0.52	0.47	0.57	0.90	1.13
reused motion	0.23	0.32	0.39	0.35	0.39	0.69	0.70	0.75	0.94	1.02

Appendix

Table 11: Same-data comparison, ground contact and activity (test, first 60 frames, five seeds; Ours and UniMate as in Tab. 10 ). Pen.: share of frames below the ground (real 0). Skate and Cov.: closer to the real value is better. Speed: joint speed relative to the real clips. Bold: lower Pen., or a smaller absolute difference from the real value for Skate and Cov., with the paired 95% interval over rigs excluding zero.

		FID desc $\downarrow$		FID kin M2M $\downarrow$		FID kin Bk. $\downarrow$		Pen. $\downarrow$		Skate			Speed
Test clips	Clips	Ours	Uni.	Ours	Uni.	Ours	Uni.	Ours	Uni.	Ours	Uni.	Real	Ours	Uni.
All	1,062	4.83	4.32	2.00	2.52	1.85	2.18	0.24	0.28	0.33	0.24	0.35	0.93	0.85
ID-clip	172	7.18	5.96	2.40	2.57	2.10	2.22	0.25	0.27	0.34	0.25	0.33	0.98	0.93
No training clip	890	4.58	4.22	0.55	1.48	0.56	1.13	0.24	0.28	0.33	0.24	0.35	0.92	0.83
novel motion	453	9.63	7.95	1.15	2.17	1.05	1.70	0.27	0.29	0.26	0.21	0.30	0.90	0.83
reused motion	437	0.65	1.21	0.06	0.72	0.08	0.47	0.23	0.27	0.39	0.27	0.39	0.94	0.83

Appendix

Table 12: Same-data comparison with UniMate tuned on dev FID desc (guidance 3; test, first 60 frames, five seeds; Ours as in Tab. 10 ). FID kin : Motion2Motion (M2M) and Bailando (Bk.) releases of the kinetic features. Skate: closer to the real value is better; Speed: relative to the real clips (target 1). Bold: lower FID desc , FID kin or Pen., or closer to the real value for Skate and Speed, the paired 95% interval over rigs excluding zero.

Method	FID desc $\downarrow$	Skate $\downarrow$	Slide $\downarrow$	Cov. $\rightarrow$
Rigs unseen by all three: capybara and emu, 6 rigs, 635 clips
Real clips	–	0.213	1.03	0.199
AnyTop † [ 12 ]	24.63	0.759	10.65	0.358
UniMate [ 31 ]	3.32	0.268	1.59	0.220
TopX	1.19	0.208	1.27	0.234
Trained on by both baselines: 6 Truebones rigs, 62 clips

Appendix

Table 13: Released weights (test, first 60 frames, five seeds per clip). TopX is the main model, trained on four corpora. Top: the two held-out species, on rigs that none of the three methods was trained on; bottom: the Truebones test rigs, on which both baselines were trained. † Unconditional and transductive. Real clips give the reference values.

Bucket	Rigs / clips	Real–real	Full	Frame table	Joint table	Eigvec. + SignNet	$-$ aug.
OOD-tree	218 / 320	0.142	1.78 $\pm$ 0.03	1.88 $\pm$ 0.03	1.87 $\pm$ 0.04	1.83 $\pm$ 0.03	1.95 $\pm$ 0.04
OOD-plan	45 / 62	6.04	11.1 $\pm$ 0.2	11.7 $\pm$ 0.1	11.5 $\pm$ 0.3	11.5 $\pm$ 0.2	12.1 $\pm$ 0.2
OOD-new-species ∗	9 / 47	104	82.4 $\pm$ 0.8	84.4 $\pm$ 1.0	83.7 $\pm$ 0.7	83.6 $\pm$ 1.3	91.8 $\pm$ 1.8
OOD-rig ∗	6 / 62	0.914	1.01 $\pm$ 0.11	1.59 $\pm$ 0.04	1.12 $\pm$ 0.11	1.17 $\pm$ 0.15	1.03 $\pm$ 0.03

Appendix

Table 14: Table 4 with its uncertainty: KID desc as the mean over the five sampling seeds

\pm

its 95% half-width over them. Columns: full recipe, learned frame table, learned joint table, eigenvectors + SignNet, without augmentation. ∗ Fewer than 20 rigs.

Figure 3: One test clip from each of five OOD buckets, real and TopX (guidance 2, seed 7). Strips show the real clip above ours at equal times; the strobe panel shows the real clip on the left and overlays five poses spaced along the real clip’s root path. Headers give the bucket and the caption.

Figure 4: Four more humanoid rigs with no training clip, drawn as in Fig. 2 (a): TopX above UniMate.

Mesh (author)	Licence	Figure
Defeat Idle (vicente betoret ferrero)	CC BY 4.0	2 (a)
Lowpoly Dog Walk (timesen)	CC BY 4.0	2 (a)
Dey Flair Dancing (jdey123)	CC BY 4.0	2 (a)
Back Flip To Uppercut (1) (marcolinadesign)	CC BY 4.0	2 (a)
Low poly fox running animation (dragonsnap)	CC BY 4.0	3
fario3 (masterdef)	CC BY 4.0	3

Appendix

Table 15: Meshes under public licences in Figs. 1 , 2 , 3 and 4 ; the human of Fig. 1 is SMPL+H [ 37 ] . † Title shortened.

	All		Emu
	R@1	Shuf.	R@1	Shuf.
Real clips, first 60 frames	0.896	–	0.871	–
Real clips, full length	0.929	–	0.933	–
TopX, generating 60 frames	0.915 $\pm$ 0.007	0.122	0.928 $\pm$ 0.006	0.137
TopX, clip length, first 60 frames	0.932 $\pm$ 0.007	0.113	0.922 $\pm$ 0.016	0.127
TopX, clip length, full	0.953 $\pm$ 0.004	0.120	0.954 $\pm$ 0.013	0.137

Appendix

Table 16: Caption-to-motion R@1 within rigs of the held-out game species (pools of 8, chance 0.125): mean and 95% half-width over five seeds, and the R@1 with captions shuffled (Shuf.). All: 439 clips on 6 rigs; emu: 181 clips on 3 rigs.

Text-to-Motion Generation

Text-to-motion generation converts natural-language descriptions into semantically aligned, temporally coherent 3D human movement.

See all 96 papers

Sep 4, 2026

UniMate: One Unified Model to Animate Diverse Skeletons

Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference. We present UniMate, a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text prompt, with no test-time optimization or per-skeleton retraining. UniMate introduces a topology-aware diffusion transformer, which integrates skeletal topology into attention via three mechanisms: (1) a graph-aware attention bias from pairwise joint relations and geodesic distances; (2) a spectral rotary position embedding generalizing RoPE to arbitrary kinematic trees via the graph Laplacian; and (3) a global topological conditioner attention-pooled from the rest-pose skeleton. We also curate UniML3D, 13,006 motion sequences spanning bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid objects with unified canonicalization and text pairing. Trained on this dataset, UniMate outperforms state-of-the-art baselines in quality, generalization, and efficiency, and supports zero-shot cross-topology transfer, in-betweening, expansion, and text-guided editing. Our project page is available at https://linzhanmou.com/unimate/.

Linzhan Mou, Jiahui Lei, Zhiyang Dou +4

Princeton University, USA · University of California, Berkeley, USA · Massachusetts Institute of Technology, USA +1

Text-to-Motion Generation Motion Diffusion Models Diffusion Transformer Human Motion Generation

Ask PDF

Oct 3, 2026

TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons

Text-driven motion editing modifies an existing motion sequence according to a text instruction while preserving the content of the source motion. Existing methods are typically built for a single, fixed skeletal topology, which limits their use in animation pipelines where characters differ in joint count and skeletal hierarchy. We present Topology-Aware Motion Editor (TAME), a flow-matching transformer that edits motions on humanoid skeletons of varying topology. TAME represents motion as per-joint, per-frame tokens and models interactions among joints, across frames, and with the text instruction through skeletal, temporal, and text cross-attention layers. To make the skeletal attention follow each character's hierarchy, TAME replaces full joint attention with Topology-Constrained Skeletal Propagation (TCSP), which restricts attention to one-hop kinematic neighbors in the skeleton's adjacency matrix. We further introduce Edit-Focused Representation Alignment (EFRA), a self-distilled representation alignment strategy that aligns student features with cleaner EMA-teacher features exclusively on edit-relevant joint-time tokens, making edits faithful to the instruction. To make this setting trainable and comparable, we construct TopoMotionFix, a multi-topology extension of MotionFix with seen- and unseen-topology evaluation protocols. TAME outperforms previous methods in edit alignment and source preservation on MotionFix and reliably edits motions on unseen skeletons in TopoMotionFix.

Qichen Zheng, Siyuan Yang, Chong Wang +4

Nanyang Technological University · KTH Royal Institute of Technology · Lancaster University

Human Motion Generation

Ask PDF

Jul 2, 2026

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

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.

Yuhao Zhang, Gerard Pons-Moll, Tolga Birdal

Imperial College London · University of Tübingen, Tübingen AI Center

Generative Modeling Motion Representation Learning

Ask PDF

Abstract

Text-to-Motion Generation

Explore similar work

UniMate: One Unified Model to Animate Diverse Skeletons

TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons

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