Pith. sign in

REVIEW 7 cited by

DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.01476 v3 pith:23FCDGH7 submitted 2024-06-03 cs.CV

classification cs.CV
keywords videodistillationmotionsphysics-basedpriorsproposecontentdiffusion
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Dynamic 3D interaction has been attracting a lot of attention recently. However, creating such 4D content remains challenging. One solution is to animate 3D scenes with physics-based simulation, which requires manually assigning precise physical properties to the object or the simulated results would become unnatural. Another solution is to learn the deformation of 3D objects with the distillation of video generative models, which, however, tends to produce 3D videos with small and discontinuous motions due to the inappropriate extraction and application of physics priors. In this work, to combine the strengths and complementing shortcomings of the above two solutions, we propose to learn the physical properties of a material field with video diffusion priors, and then utilize a physics-based Material-Point-Method (MPM) simulator to generate 4D content with realistic motions. In particular, we propose motion distillation sampling to emphasize video motion information during distillation. In addition, to facilitate the optimization, we further propose a KAN-based material field with frame boosting. Experimental results demonstrate that our method enjoys more realistic motions than state-of-the-arts do.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting

    cs.GR 2026-04 unverdicted novelty 7.0 of 10

    FieryGS integrates LLM-based material reasoning, volumetric combustion simulation, and a unified renderer with 3D Gaussian Splatting to generate physically plausible and user-controllable fire in in-the-wild scenes.

  2. Floating Radiance Networks

    cs.CV 2026-08 conditional novelty 6.0 of 10

    FlaRe combines per-primitive latent radiance descriptors on planar Gaussians with a shared decoder and hardware ray tracing, making rendering, secondary rays, editing, and mesh extraction work in one scene model.

  3. muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards

    cs.CV 2026-08 conditional novelty 6.0 of 10

    muSync-GS couples weather and road-shape edits in driving videos to a calibrated vehicle-dynamics model, so the synthesized ego motion and telemetry change with the same controls that drive the visual edits.

  4. InteRecon: Towards Reconstructing Interactivity of Personal Memorable Items in Mixed Reality

    cs.HC 2025-02 conditional novelty 6.0 of 10

    The paper demonstrates a prototype that lets people turn cherished objects into interactive AR versions that preserve their original motions, buttons, and embedded media.

  5. Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

    cs.CV 2025-08 reject novelty 5.0 of 10

    A supervised 3D U-Net predicts per-voxel material fields from CLIP feature grids, enabling fast MPM-based animation, but the reported evidence depends on pseudo-labels and a VLM judge from the same model family as the...

  6. AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing

    cs.CV 2025-08 conditional novelty 5.0 of 10

    An anchor-graph structured 3D Gaussians representation, with graph-based feature propagation and region growing, achieves cleaner instance-level object selection and better editing/simulation results than free-Gaussia...

  7. PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

    cs.CV 2025-06 reject novelty 5.0 of 10

    PhysRig animates articulated 3D objects by simulating them as deformable soft bodies driven by an embedded skeleton, and learns the material and motion parameters with a differentiable physics simulator.

Pith tools