ReconPhys is the first feedforward neural network that jointly reconstructs 3D geometry and appearance via Gaussian Splatting while estimating physical attributes from a single monocular video using self-supervised training.
arXiv preprint arXiv:2303.05512 (2023)
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
MoSA learns residual stress operators on an isotropic backbone using a physics-informed cascaded network and motion constraints to capture mild anisotropy and heterogeneity for improved real-to-sim dynamics.
MeGAS augments 3D Gaussian Splatting with temperature attributes, heat advection-diffusion, and MPM phase transitions to produce physically consistent thermomechanical scene behavior while preserving photorealistic rendering.
NeuROK learns a data-driven latent kinematic parameterization on a large 4D dataset to generate realistic object deformations by simulating dynamics only in low-dimensional latent space via Lagrangian mechanics.
R5DGS augments physics-driven 4D Gaussian splatting with identity encodings and centroid-only rigid-body dynamics to enable semantic open-vocabulary retrieval and 11 FPS faster extrapolation.
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
PhysLayer is a framework that decomposes images into depth layers, simulates physics with depth awareness, and synthesizes videos guided by language for more plausible animations.
LIVE-GS uses an LLM to predict physical parameters from static Gaussian assets in 10 seconds for physics-aware VR interactions, validated by interviews, baseline comparisons, and user studies.
The paper's stated CA-World counterfactual claim is absent from the body, which instead describes the SAM3D-Phys pipeline for multi-object interactive reconstruction and simulation.
citing papers explorer
-
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
ReconPhys is the first feedforward neural network that jointly reconstructs 3D geometry and appearance via Gaussian Splatting while estimating physical attributes from a single monocular video using self-supervised training.
-
MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
MoSA learns residual stress operators on an isotropic backbone using a physics-informed cascaded network and motion constraints to capture mild anisotropy and heterogeneity for improved real-to-sim dynamics.
-
MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing
MeGAS augments 3D Gaussian Splatting with temperature attributes, heat advection-diffusion, and MPM phase transitions to produce physically consistent thermomechanical scene behavior while preserving photorealistic rendering.
-
NeuROK: Generative 4D Neural Object Kinematics
NeuROK learns a data-driven latent kinematic parameterization on a large 4D dataset to generate realistic object deformations by simulating dynamics only in low-dimensional latent space via Lagrangian mechanics.
-
R5DGS: Semantic-Aware 4D Gaussian Splatting with Rigid Body Constraints for Efficient Dynamic Scene Reconstruction
R5DGS augments physics-driven 4D Gaussian splatting with identity encodings and centroid-only rigid-body dynamics to enable semantic open-vocabulary retrieval and 11 FPS faster extrapolation.
-
LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
-
PhysLayer: Language-Guided Layered Animation with Depth-Aware Physics
PhysLayer is a framework that decomposes images into depth layers, simulates physics with depth awareness, and synthesizes videos guided by language for more plausible animations.
-
LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting
LIVE-GS uses an LLM to predict physical parameters from static Gaussian assets in 10 seconds for physics-aware VR interactions, validated by interviews, baseline comparisons, and user studies.
-
CA-World: Multi-Object Counterfactual Alignment for Efficient Interactive-Ready Reconstruction
The paper's stated CA-World counterfactual claim is absent from the body, which instead describes the SAM3D-Phys pipeline for multi-object interactive reconstruction and simulation.