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.
hub
Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
CoGS is a compositional Gaussian splatting framework that decomposes monocular videos into human, object, and scene branches with a six-stage optimization to improve dynamic human-object scene reconstruction.
C4G introduces compact timestamp-conditioned Gaussian query tokens that aggregate full temporal context to decode 3D Gaussians with timestamp-modulated positions for feed-forward 4D reconstruction from monocular video, plus a diffusion-based rendering module and extension to 4D feature fields.
SplatWeaver uses cardinality Gaussian experts and pixel-level routing to dynamically allocate varying numbers of Gaussian primitives for generalizable novel view synthesis.
Cloth-HUGS uses layered Gaussians for body and cloth with SMPL-driven deformation and physics constraints to improve clothed human reconstruction over prior single-representation methods.
Splats in Splats++ embeds messages into 3DGS via importance-graded SH encryption, hash-grid opacity mapping, and a gradient-gated consistency loss, achieving higher fidelity and robustness than prior methods.
TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.
The paper presents a multimodal framework, dataset, and reconstruction pipeline to create immersive volumetric videos supporting large 6-DoF audiovisual interaction from real multi-view captures.
MoGaF groups Gaussians by motion in 4D splatting representations to enable stable long-term forecasting of dynamic scenes.
PerpetualWonder introduces a closed-loop generative simulator with a unified physical-visual representation for long-horizon action-conditioned 4D scene generation from one image.
A generative video model conditioned on pixel-aligned 3D renderings produces consistent dynamic 3D Gaussian splats from monocular video and sets new SOTA in 4D reconstruction.
Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.
SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
PanopticQuery lifts 2D semantic predictions into globally consistent 4D groundings via neural field optimization and sets new state-of-the-art results on complex language queries for attributes, actions, and interactions.
HOIGS adds a cross-attention HOI module to Gaussian Splatting that combines HexPlane human features with Cubic Hermite Spline object features to model interaction-induced deformations.
PhysMorph-GS injects visual supervision via deformation gradients in differentiable physics simulation and uses phased Chamfer-guided plasticity to reduce silhouette error by up to 49.9% compared to physics-only baselines.
BulletGen enhances 4D dynamic scene reconstruction from monocular videos by supervising Gaussian optimization with diffusion-generated frames aligned at a bullet-time step, achieving SOTA on novel-view synthesis and tracking.
End-to-end neural pipeline extracts hand geometry from unmasked limited-view images and registers it to a personalized tetrahedral model via volumetric offsets, achieving SOTA on over 12,000 sequences.
Dynamic 3DGS models achieve lower PSNR on egocentric videos than exocentric ones, with the gap arising from static content reconstruction.
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.
-
CoGS: Compositional Dynamic Human-Object Scenes Gaussian Splatting from Monocular Video
CoGS is a compositional Gaussian splatting framework that decomposes monocular videos into human, object, and scene branches with a six-stage optimization to improve dynamic human-object scene reconstruction.
-
Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
C4G introduces compact timestamp-conditioned Gaussian query tokens that aggregate full temporal context to decode 3D Gaussians with timestamp-modulated positions for feed-forward 4D reconstruction from monocular video, plus a diffusion-based rendering module and extension to 4D feature fields.
-
SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
SplatWeaver uses cardinality Gaussian experts and pixel-level routing to dynamically allocate varying numbers of Gaussian primitives for generalizable novel view synthesis.
-
CLOTH-HUGS: Cloth Aware Human Gaussian Splatting
Cloth-HUGS uses layered Gaussians for body and cloth with SMPL-driven deformation and physics constraints to improve clothed human reconstruction over prior single-representation methods.
-
Splats in Splats++: Robust and Generalizable 3D Gaussian Splatting Steganography
Splats in Splats++ embeds messages into 3DGS via importance-graded SH encryption, hash-grid opacity mapping, and a gradient-gated consistency loss, achieving higher fidelity and robustness than prior methods.
-
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.
-
Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement
The paper presents a multimodal framework, dataset, and reconstruction pipeline to create immersive volumetric videos supporting large 6-DoF audiovisual interaction from real multi-view captures.
-
Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
MoGaF groups Gaussians by motion in 4D splatting representations to enable stable long-term forecasting of dynamic scenes.
-
PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation
PerpetualWonder introduces a closed-loop generative simulator with a unified physical-visual representation for long-horizon action-conditioned 4D scene generation from one image.
-
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
A generative video model conditioned on pixel-aligned 3D renderings produces consistent dynamic 3D Gaussian splats from monocular video and sets new SOTA in 4D reconstruction.
-
Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting
Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.
-
Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars
SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
-
PanopticQuery: Unified Query-Time Reasoning for 4D Scenes
PanopticQuery lifts 2D semantic predictions into globally consistent 4D groundings via neural field optimization and sets new state-of-the-art results on complex language queries for attributes, actions, and interactions.
-
HOIGS: Human-Object Interaction Gaussian Splatting
HOIGS adds a cross-attention HOI module to Gaussian Splatting that combines HexPlane human features with Cubic Hermite Spline object features to model interaction-induced deformations.
-
PhysMorph-GS: Render-Guided Volumetric Morphing with Differentiable Physics
PhysMorph-GS injects visual supervision via deformation gradients in differentiable physics simulation and uses phased Chamfer-guided plasticity to reduce silhouette error by up to 49.9% compared to physics-only baselines.
-
BulletGen: Improving 4D Reconstruction with Bullet-Time Generation
BulletGen enhances 4D dynamic scene reconstruction from monocular videos by supervising Gaussian optimization with diffusion-generated frames aligned at a bullet-time step, achieving SOTA on novel-view synthesis and tracking.
-
VEPHand: View-Efficient Photometric Hand Performance Capture at Scale
End-to-end neural pipeline extracts hand geometry from unmasked limited-view images and registers it to a personalized tetrahedral model via volumetric offsets, achieving SOTA on over 12,000 sequences.
-
Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction
Dynamic 3DGS models achieve lower PSNR on egocentric videos than exocentric ones, with the gap arising from static content reconstruction.