RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation

• URL: http://arxiv.org/abs/2608.28219v1
• Date: Fri, 28 Aug 2026 11:36:44 GMT
• Title: RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation
• Abstract summary: Cross-identity character animation aims to drive a target identity from a reference image to follow the motion of a source character from a driving video.<n>We introduce Reference-Aware Structural Alignment (RASA), a framework that disentangles spatial mapping from motion control.<n>Our work establishes a new paradigm showing disentangled spatial and motional priors are key to robust character animation.
• Score: 85.41886214825894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-identity character animation aims to drive a target identity from a reference image to follow the motion of a source character from a driving video. The core challenge lies in the inherent entanglement of two capabilities: cross-identity spatial mapping (aligning position, scale, and skeletal proportions) and motion control (refining joint articulation, volumetric consistency, and view coherence). We introduce Reference-Aware Structural Alignment (RASA), a framework that disentangles spatial mapping from motion control by injecting structured priors into a Diffusion Transformer (DiT). Our approach has two stages. First, a Spatial Prior Calibrator (SPC) fuses reference identity with driving pose to generate a spatially grounded initial noise latent, ensuring correct positioning, scaling, and alignment with the driving skeleton. Second, an Inherent Motional Guider (IMG) encodes shape-agnostic SMPL articulation parameters into a semantic motion vector beyond appearance-biased 2D keypoints. Injected into intermediate DiT layers, this vector complements the base pose condition for anatomically consistent articulation and view-aware volumetric refinement. We curate CIM-Bench, a high-quality benchmark with rigorous curation, for evaluation. Extensive experiments show RASA significantly outperforms state-of-the-art methods in motion fidelity and visual quality. Our work establishes a new paradigm showing disentangled spatial and motional priors are key to robust character animation. Project page: https://hidream.ai.github.io/RASA/

Related papers

• OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention [0.4790056963046066]
  Controllable video generation demands independent command of the camera and the subject.<n> OrthoMotion routes camera motion into a geometric channel, a norm-preserving rotation of the rotary position embedding (RoPE) phase, and subject motion into a semantic channel.<n>To our knowledge OrthoMotion is the first method to guarantee disentanglement by construction rather than hope for it to emerge.
  arXiv  Detail & Related papers  (2026-06-22T04:15:14Z)
• MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons [56.68975315643491]
  We present the first fully end-to-end framework in which Videoto-Pose and Pose-to-Rotation are learnable and optimized jointly.<n>We show that our method reduces rotation error from 17 degrees to 10 degrees, and to 6.54 degrees on unseen skeletons, while achieving 20x faster inference than mesh-based pipelines.
  arXiv  Detail & Related papers  (2026-04-30T17:16:38Z)
• ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes [55.32681167870698]
  Video-informed Pose Spaces (ViPS) is a feed-forward framework that discovers the latent distribution of valid articulations for auto-rigged meshes.<n>ViPS transfers generative video priors into a universal distribution over a given rig parameterization.<n>Our evaluations show that ViPS matches the performance of state-of-the-art methods trained on synthetic artist-created 4D data in both plausibility and diversity.
  arXiv  Detail & Related papers  (2026-04-19T21:21:11Z)
• AG-EgoPose: Leveraging Action-Guided Motion and Kinematic Joint Encoding for Egocentric 3D Pose Estimation [11.399976049695212]
  AG-EgoPose is a novel dual-stream framework that integrates short- and long-range motion context with fine-grained spatial cues for robust pose estimation.<n>Our framework features two parallel streams: A spatial stream uses a weight-sharing ResNet-18 encoder-decoder to generate 2D joint heatmaps.<n>A temporal stream uses a ResNet-50 backbone to extract visual features, which are then processed by an action recognition backbone to capture the motion dynamics.
  arXiv  Detail & Related papers  (2026-03-26T08:46:51Z)
• Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints [87.13154261503168]
  Motion-controllable video generation is crucial for egocentric applications in virtual reality and embodied AI.<n>Existing methods often struggle to achieve 3D-consistent fine-grained hand articulation.<n>We propose a novel framework that generates egocentric videos from a single reference frame.
  arXiv  Detail & Related papers  (2026-03-12T10:02:23Z)
• DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning [24.808926786222376]
  We present DreamActor-M2, a universal animation framework that reimagines motion conditioning as an in-context learning problem.<n>Our approach follows a two-stage paradigm. First, we bridge the input modality gap by fusing reference appearance and motion cues into a unified latent space.<n>Second, we introduce a self-bootstrapped data synthesis pipeline that curates pseudo cross-identity training pairs.
  arXiv  Detail & Related papers  (2026-01-29T13:43:17Z)
• STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding [31.38893861328115]
  Video generation has recently made striking visual progress, but maintaining coherent object motion and interactions remains difficult.<n>We present STANCE, an image-to-video framework that addresses both issues with two simple components.
  arXiv  Detail & Related papers  (2025-10-16T11:50:38Z)
• Learning Spatial Decay for Vision Transformers [50.63391799053993]
  Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases.<n>Existing approaches introduce data-independent spatial decay based on fixed distance metrics.<n>We present the first successful adaptation of data-dependent spatial decay to 2D vision transformers.
  arXiv  Detail & Related papers  (2025-08-13T06:18:32Z)
• SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes [32.324844649352166]
  Animation retargetting applies sparse motion description to a character mesh to produce a semantically plausible and temporally coherent full-body sequence.<n>We propose Self-supervised Motion Fields (SMF), a self-supervised framework that is trained with only sparse motion representations.<n>Our architecture comprises dedicated spatial and temporal gradient predictors, which are jointly trained in an end-to-end fashion.
  arXiv  Detail & Related papers  (2025-04-07T08:42:52Z)
• DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation [63.781450025764904]
  We propose DynamiCtrl, a novel framework for human animation in video DiT architecture.<n>We use a shared VAE encoder for human images and driving poses, unifying them into a common latent space.<n>We also introduce the "Joint-text" paradigm, which preserves the role of text embeddings to provide global semantic context.
  arXiv  Detail & Related papers  (2025-03-27T08:07:45Z)
• STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition [50.064502884594376]
  We study the problem of human action recognition using motion capture (MoCap) sequences. We propose a novel Spatial-Temporal Mesh Transformer (STMT) to directly model the mesh sequences. The proposed method achieves state-of-the-art performance compared to skeleton-based and point-cloud-based models.
  arXiv  Detail & Related papers  (2023-03-31T16:19:27Z)

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.