arXiv Computer Vision
PhysCreator: Creating Physically-Attributed 3D Assets at Will
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 12
Neural Voxel Dynamics: Learning Volumetric Feature Advection for 3D Physics in V-JEPA Latent Space
Neural Voxel Dynamics introduces a self‑supervised framework that learns 3D latent dynamics from monocular video by unprojecting V‑JEPAs features into a voxel grid using depth priors. It then applies Volumetric Feature Advection, an action‑conditioned transition model, to predict the evolution of these latent features directly in 3D, without relying on privileged physics‑engine states. The method is evaluated on synthetic and real datasets, demonstrating predictive fidelity, 3D geometric consistency, and physical plausibility via Physics‑IQ metrics.
arXiv Computer Vision
Oct 22
AutoPhyX: Automatic Text-Condition Physics Property Generation
AutoPhyX is a text-conditioned framework that predicts spatially-varying physical properties for 4D physical simulation. It uses a novel part-controllable data generation pipeline to create fine-grained, semantically distinct 3D assets paired with diverse parameters and text descriptions. The model employs cross-modal modulation to dynamically adjust visual features based on text, enabling accurate, physically plausible parameter assignment across various 3D representations in a single forward pass.
Hugging Face Trending Papers
Sep 3
Sparse auto-regressive modeling for scene generation from multi-view images
The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. By representing only occupied voxels in a compact latent space and training a masked autoregressive transformer with photometric supervision via differentiable 3D Gaussian Splatting, the method predicts missing latent tokens and spatial support, enabling efficient and spatially consistent generation of unseen regions. Experiments on synthetic indoor scenes and RealEstate10k demonstrate higher novel‑view quality and real‑world applicability compared to prior work.
arXiv Machine Learning
Sep 4
Sparse auto-regressive modeling for scene generation from multi-view images
The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. It learns a compact voxel‑aligned latent space using photometric supervision via differentiable 3D Gaussian Splatting, and employs a masked autoregressive transformer to predict missing voxel occupancy and latent tokens. Experiments on synthetic indoor scenes and RealEstate10k show that SPAR3S achieves higher novel‑view quality than prior methods and generalizes to real‑world data.
arXiv Computer Vision
6d ago
Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
arXiv:2603.22782v3 Announce Type: replace Abstract: Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity...
arXiv Computer Vision
Sep 1
Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos
arXiv:2608.31025v1 Announce Type: new Abstract: Inferring object dynamics from visual observations is essential for intelligent agents to reason about and interact with the physical world, yet remain...