Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization

• URL: http://arxiv.org/abs/2606.02000v1
• Date: Mon, 01 Jun 2026 09:56:48 GMT
• Title: Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization
• Abstract summary: We propose a render-free framework that conditions video generation directly on compressed 3D human mesh tokens.<n>This representation preserves full 3D geometric information while enabling a unified token-based generation pipeline.<n> Experimental results demonstrate strong performance on human motion control benchmarks, while reducing artifacts induced by view-dependent 2D guidance and trajectory-pose mismatches during editing.
• Score: 41.562044736774816
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Diffusion models have shown remarkable success in video generation. However, whether such models are truly aware of the 3D structure underlying visual observations, rather than simply reproducing plausible 2D projections, remains an open question. In this work, we investigate this question through human motion control, a task that requires precise modelling of 3D human geometry, motion, camera viewpoint, and scene context. Unlike prior methods that rely on rendered 2D motion guidance videos, we propose a render-free framework that conditions video generation directly on compressed 3D human mesh tokens. This representation preserves full 3D geometric information while enabling a unified token-based generation pipeline that processes video tokens jointly with motion tokens in a DiT-based architecture. This design requires the model to reason jointly about appearance, 3D structure, and camera viewpoint during video generation. Experimental results demonstrate strong performance on human motion control benchmarks, while reducing artifacts induced by view-dependent 2D guidance and trajectory-pose mismatches during editing. These findings suggest that video diffusion models, when equipped with mesh tokenization, can better capture complex 3D human structures and their interactions with the surrounding environment.

Related papers

• 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation [29.389246008057473]
  2D poses rigidly bind motion to the driving viewpoint, precluding novel-view synthesis.<n>3DiMo trains a motion encoder with a pretrained video generator to distill driving frames into compact, view-agnostic motion tokens.<n>Experiments confirm that 3DiMo faithfully reproduces driving motions with flexible, text-driven camera control.
  arXiv  Detail & Related papers  (2026-02-03T17:59:09Z)
• Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians [7.051077403685518]
  Humans excel at forecasting the future dynamics of a scene given just a single image.<n>Video generation models that can mimic this ability are an essential component for intelligent systems.<n>Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation.
  arXiv  Detail & Related papers  (2026-01-02T13:04:47Z)
• ManipDreamer3D : Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory [56.06314177428745]
  We present ManipDreamer3D for generating plausible 3D-aware robotic manipulation videos from the input image and the text instruction.<n>Our method generates robotic videos with autonomously planned 3D trajectories, significantly reducing human intervention requirements.
  arXiv  Detail & Related papers  (2025-08-29T10:39:06Z)
• Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos [71.24593306228145]
  We propose to improve dynamic segmentation in 3D by fusing motion segmentation predictions from a 2D-based model into layered radiance fields.<n>We address this issue through test-time refinement, which helps the model to focus on specific frames, thereby reducing the data complexity.<n>This demonstrates that 3D techniques can enhance 2D analysis even for dynamic phenomena in a challenging and realistic setting.
  arXiv  Detail & Related papers  (2025-06-05T19:46:48Z)
• Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach [54.559847511280545]
  We present a novel video generation framework that integrates 3-dimensional geometry and dynamic awareness.<n>To achieve this, we augment 2D videos with 3D point trajectories and align them in pixel space.<n>The resulting 3D-aware video dataset, PointVid, is then used to fine-tune a latent diffusion model.
  arXiv  Detail & Related papers  (2025-02-05T21:49:06Z)
• Generating 3D-Consistent Videos from Unposed Internet Photos [68.944029293283]
  We train a scalable, 3D-aware video model without any 3D annotations such as camera parameters. Our results suggest that we can scale up scene-level 3D learning using only 2D data such as videos and multiview internet photos.
  arXiv  Detail & Related papers  (2024-11-20T18:58:31Z)
• Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior [57.986512832738704]
  We present a new framework Sculpt3D that equips the current pipeline with explicit injection of 3D priors from retrieved reference objects without re-training the 2D diffusion model. Specifically, we demonstrate that high-quality and diverse 3D geometry can be guaranteed by keypoints supervision through a sparse ray sampling approach. These two decoupled designs effectively harness 3D information from reference objects to generate 3D objects while preserving the generation quality of the 2D diffusion model.
  arXiv  Detail & Related papers  (2024-03-14T07:39:59Z)
• Neural Groundplans: Persistent Neural Scene Representations from a Single Image [90.04272671464238]
  We present a method to map 2D image observations of a scene to a persistent 3D scene representation. We propose conditional neural groundplans as persistent and memory-efficient scene representations.
  arXiv  Detail & Related papers  (2022-07-22T17:41:24Z)
• Unsupervised object-centric video generation and decomposition in 3D [36.08064849807464]
  We propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects.
  arXiv  Detail & Related papers  (2020-07-07T18:01:29Z)

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.