UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation

• URL: http://arxiv.org/abs/2608.09143v1
• Date: Mon, 10 Aug 2026 05:42:58 GMT
• Title: UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation
• Abstract summary: We ground motion editing directly within text-to-motion generation across data, architecture, and inference.<n>At the data level, we develop a closed-loop synthesis-and-verification pipeline that produces Omni-MoEdit, a large-scale dataset spanning body-part, amplitude, temporal, action, and style edits.<n>At the architectural level, we introduce UniMoFlow, a unified latent flow-matching model that shares broad semantic kinematic and semantics knowledge between generation and editing.<n>We augment standard evaluations with semantics-aware metrics to account for valid edits that inherently deviate from a single ground-truth reference.
• Score: 31.218236544871967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in scale and semantic diversity. To overcome this bottleneck, we ground motion editing directly within text-to-motion generation across data, architecture, and inference. At the data level, we develop a closed-loop synthesis-and-verification pipeline that produces Omni-MoEdit, a large-scale dataset spanning body-part, amplitude, temporal, action, and style edits. At the architectural level, we introduce UniMoFlow, a unified latent flow-matching model that shares broad semantic and kinematic knowledge between generation and editing. At the inference level, SAFE (Source-Anchored Flow Editing) complements UniMoFlow with controllable, source-anchored refinement. Furthermore, we augment standard evaluations with semantics-aware metrics to account for valid edits that inherently deviate from a single ground-truth reference. Extensive experiments demonstrate improved target-text alignment, edit effectiveness, and cycle consistency, while maintaining competitive source fidelity and text-to-motion generation quality.

Related papers

• Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editing [78.44034844227868]
  Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions.<n>Change and Invariance Motion Editing (CIME) is a unified framework that comprehensively decouples change and invariance into spatial pose and temporal rhythm dimensions.<n>Experiments on the MotionFix and STANCE Adjustment datasets demonstrate that CIME achieves state-of-the-art performance in editing alignment and structural fidelity.
  arXiv  Detail & Related papers  (2026-08-17T01:54:44Z)
• Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing [12.284953145384264]
  We address text-based 3D human motion editing, where the goal is to preserve the style and structure of a source motion while applying edits described in natural language.<n>Our goal is to create a model that understands not only this temporal aspect but also which specific joints are responsible for the change.
  arXiv  Detail & Related papers  (2026-05-31T05:09:42Z)
• Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning [55.410155357480654]
  We propose an Omni-Supervised Positive-Negative Learning framework, named OmniME.<n>Our method integrates three complementary components.<n>Experiments on the MotionFix and STANCE Adjustment datasets demonstrate that OmniME achieves state-of-the-art performance in editing alignment.
  arXiv  Detail & Related papers  (2026-05-29T08:09:51Z)
• KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and Editing [24.315720861063397]
  KGEdit is a structured semantic control framework for text-to-video (T2V) diffusion models.<n>We first construct an ambiguity-aware knowledge graph (AAKG) to disentangle and disambiguate the input prompt.<n>We then design a structured semantic injection module (SSIM) to inject semantic signals into key layers of the diffusion Transformer.
  arXiv  Detail & Related papers  (2026-05-28T07:31:22Z)
• SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing [9.343095346668665]
  SteerFlow is a model-agnostic editing framework with strong theoretical guarantees on source fidelity.<n>We introduce Trajectory Interpolation, which adaptively blends target-editing and source-reconstruction velocities to keep the editing trajectory anchored to the source.<n>Experiments on FLUX.1-dev and Stable Diffusion 3.5 Medium demonstrate that SteerFlow consistently achieves better editing quality than existing methods.
  arXiv  Detail & Related papers  (2026-04-02T07:26:13Z)
• SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing [76.349958946335]
  We present SAMA (factorized Semantic Anchoring and Motion Alignment), a framework that factorizes video editing into semantic anchoring and motion modeling.<n>First, we introduce Semantic Anchoring, which establishes a reliable visual anchor by jointly predicting semantic tokens and video latents at sparse anchor frames.<n>Second, Motion Alignment pre-trains the same backbone on motion-centric video restoration pretext tasks.
  arXiv  Detail & Related papers  (2026-03-19T17:59:51Z)
• InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing [73.51964472028392]
  We introduce the task of multi-person 3D motion editing, where a target motion is generated from a source and a text instruction.<n>To support this, we propose InterEdit3D, a new dataset with manual two-person motion change annotations, and a Text-guided Multi-human Motion Editing (TMME) benchmark.<n>InterEdit improves text-to-motion consistency and edit fidelity, achieving state-of-the-art TMME performance.
  arXiv  Detail & Related papers  (2026-03-13T15:30:51Z)
• FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing [2.7248421583285265]
  FlowDirector is a novel inversion-free video editing framework.<n>Our framework models the editing process as a direct evolution in data space.<n>To achieve localized and controllable edits, we introduce an attention-guided masking mechanism.
  arXiv  Detail & Related papers  (2025-06-05T13:54:40Z)
• MotionFix: Text-Driven 3D Human Motion Editing [52.11745508960547]
  Key challenges include the scarcity of training data and the need to design a model that accurately edits the source motion. We propose a methodology to semi-automatically collect a dataset of triplets comprising (i) a source motion, (ii) a target motion, and (iii) an edit text. Access to this data allows us to train a conditional diffusion model, TMED, that takes both the source motion and the edit text as input.
  arXiv  Detail & Related papers  (2024-08-01T16:58:50Z)
• SemanticBoost: Elevating Motion Generation with Augmented Textual Cues [73.83255805408126]
  Our framework comprises a Semantic Enhancement module and a Context-Attuned Motion Denoiser (CAMD) The CAMD approach provides an all-encompassing solution for generating high-quality, semantically consistent motion sequences. Our experimental results demonstrate that SemanticBoost, as a diffusion-based method, outperforms auto-regressive-based techniques.
  arXiv  Detail & Related papers  (2023-10-31T09:58:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.