mlsanityData to 7 Oct 2026

BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives

arXiv 2608.31113 ↗First posted 31 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varying rigid motion components and time-invariant vertex-to-component skinning weights. This yields a low-dimensional deformation space without requiring skeletons, cages, skinning weights, or rig annotations. Our architecture conditions geometry-derived deformation latents on video features through factorized spatial-temporal attention, then decodes rigid transformations blended by predicted skinning weights. Trained with trajectory reconstruction, entropy regularization, and motion-aware contrastive learning, BLARM produces accurate and temporally stable animations while recovering compact, interpretable motion structure from monocular video.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 58 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

44 of 58 references.

References · 44

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  2. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  3. 2025DINOv3cited by 1,297
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  5. 2021Neural Fields in Visual Computing and Beyondcited by 539
  6. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  7. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
  8. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 191
  9. 2025Native and Compact Structured Latents for 3D Generationcited by 157
  10. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
  11. 2023Consistent4D: Consistent 360deg Dynamic Object Generation from Monocular Videocited by 124
  12. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
32 more
  1. 2024STAG4D: Spatial-Temporal Anchored Generative 4D Gaussianscited by 102
  2. 2024Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Modelscited by 99
  3. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 91
  4. 2024Learning the 3D Fauna of the Webcited by 58
  5. 2024DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representationcited by 58
  6. 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusioncited by 55
  7. 2021KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Controlcited by 50
  8. 2025RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assetscited by 47
  9. 2025One Model to Rig Them All: Diverse Skeleton Rigging with UniRigcited by 44
  10. 2025MagicArticulate: Make Your 3D Models Articulation-Readycited by 43
  11. 2025Puppeteer: Rig and Animate Your 3D Modelscited by 41
  12. 2019Predicting Animation Skeletons for 3D Articulated Models via Volumetric Netscited by 39
  13. 2021DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinatescited by 36
  14. 2025Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesiscited by 33
  15. 2025V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Videocited by 32
  16. 2025AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animationcited by 31
  17. 2022Skeleton-free Pose Transfer for Stylized 3D Characterscited by 29
  18. 2024Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characterscited by 23
  19. 2022Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstructioncited by 21
  20. 2022Morig: Motion-aware rigging of character meshes from point cloudscited by 20
  21. 2025ShapeGen4D: Towards High Quality 4D Shape Generation from Videoscited by 20
  22. 2026Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesiscited by 15
  23. 2026ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusioncited by 15
  24. 2024Survey on Modeling of Human-made Articulated Objectscited by 14
  25. 2023Weakly-supervised 3D Pose Transfer with Keypointscited by 12
  26. 2025GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapescited by 12
  27. 2026Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Videocited by 12
  28. 2025Category-Agnostic Neural Object Riggingcited by 8
  29. 2026RigMo: Unifying Rig and Motion Learning for Generative Animationcited by 5
  30. 2026BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationcited by 4
  31. 2026ViPS: Video-informed Pose Spaces for Auto-Rigged Meshescited by 2
  32. 2026Learning Neural Deformation Representation for 4D Dynamic Shape Generationcited by 1

Built on by

Not cited yet.