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
Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting, February 2024
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 19roles
background 3polarities
background 3representative citing papers
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
MoCam unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
PaMoSplat reconstructs dynamic scenes by lifting 2D segmentations to coherent 3D Gaussian parts and estimating their motions via optical flow-guided differential evolution for higher quality rendering and faster training.
ClipGStream enables scalable flicker-free reconstruction of long dynamic multi-view videos by performing stream optimization at the clip level with clip-independent spatio-temporal fields, residual anchor compensation, and inter-clip inherited anchors.
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.
GS-Surrogate creates a canonical Gaussian field that is sequentially deformed by simulation parameters to enable real-time, controllable 3D exploration of ensemble data while separating simulation variations from visualization adjustments.
SparseCam4D achieves spatio-temporally consistent high-fidelity 4D reconstruction from sparse cameras via a Spatio-Temporal Distortion Field that corrects inconsistencies in generative observations.
MoGaF groups Gaussians by motion in 4D splatting representations to enable stable long-term forecasting of dynamic scenes.
Robust Dreamer uses Latent Gaussian Memory anchored to diffusion latents and Deviation Learning with a Dynamic Deviation Archive to reduce drift in long-horizon action-controlled image-to-video generation, reporting SOTA results on ScanNet, DL3DV, and OmniWorldGame.
DeGO decouples rigid and nonrigid motion in Gaussian occupancy prediction via factorized 4D distillation from VGGT, reporting SOTA results on Occ3D-NuScenes with 13.5% gains on human-centric cases.
PD-4DGS decomposes 4DGS into static scaffold, global deformation, and local refinement layers using hierarchical decomposition and custom losses, achieving over 60% bitstream reduction and reducing first-frame latency to about 1.7 seconds on 2 Mbps links.
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.
Splatography improves dynamic 3D reconstruction from sparse multi-view videos by splitting foreground and background Gaussian representations and applying tailored deformation learning for each.
DS-StyleGaussian integrates a 2D-pretrained decoder with feature Gaussian splatting and deferred stylization to achieve view-consistent zero-shot 3D style transfer from a single style image.
TrioMan is a tri-module data augmentation framework using a Generator for pose/camera perturbations, a Refiner with one-step diffusion, and an Examiner with dual-branch attention to improve 3D avatar learning from monocular videos, claiming better results than prior methods on two benchmarks.
Flow4DGS-SLAM uses optical flow to generate motion masks, initialize poses, and guide 4D Gaussian modeling with scene flow and GMM for temporal properties, claiming SOTA results in dynamic tracking and reconstruction.
GeoRect4D couples 3D Gaussian splatting with a single-step diffusion rectifier via degradation-aware feedback and progressive optimization to improve fidelity and consistency in sparse-view dynamic 3D reconstruction.
Structure-guided dynamic 3DGS methods deliver superior reconstruction fidelity and compactness on D-NeRF while gaussian-centric methods provide higher rendering speeds at the cost of quality variability and storage.
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.
-
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
-
MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
MoCam unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
-
PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction
PaMoSplat reconstructs dynamic scenes by lifting 2D segmentations to coherent 3D Gaussian parts and estimating their motions via optical flow-guided differential evolution for higher quality rendering and faster training.
-
ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction
ClipGStream enables scalable flicker-free reconstruction of long dynamic multi-view videos by performing stream optimization at the clip level with clip-independent spatio-temporal fields, residual anchor compensation, and inter-clip inherited anchors.
-
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.
-
GS-Surrogate: Deformable Gaussian Splatting for Parameter Space Exploration of Ensemble Simulations
GS-Surrogate creates a canonical Gaussian field that is sequentially deformed by simulation parameters to enable real-time, controllable 3D exploration of ensemble data while separating simulation variations from visualization adjustments.
-
SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
SparseCam4D achieves spatio-temporally consistent high-fidelity 4D reconstruction from sparse cameras via a Spatio-Temporal Distortion Field that corrects inconsistencies in generative observations.
-
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.
-
Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
Robust Dreamer uses Latent Gaussian Memory anchored to diffusion latents and Deviation Learning with a Dynamic Deviation Archive to reduce drift in long-horizon action-controlled image-to-video generation, reporting SOTA results on ScanNet, DL3DV, and OmniWorldGame.
-
Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
DeGO decouples rigid and nonrigid motion in Gaussian occupancy prediction via factorized 4D distillation from VGGT, reporting SOTA results on Occ3D-NuScenes with 13.5% gains on human-centric cases.
-
PD-4DGS:Progressive Decomposition of 4D Gaussian Splatting for Bandwidth-Adaptive Dynamic Scene Streaming
PD-4DGS decomposes 4DGS into static scaffold, global deformation, and local refinement layers using hierarchical decomposition and custom losses, achieving over 60% bitstream reduction and reducing first-frame latency to about 1.7 seconds on 2 Mbps links.
-
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.
-
Splatography: Sparse multi-view dynamic Gaussian Splatting for filmmaking challenges
Splatography improves dynamic 3D reconstruction from sparse multi-view videos by splitting foreground and background Gaussian representations and applying tailored deformation learning for each.
-
Boosting Zero-Shot 3D Style Transfer with 2D Pre-trained Priors
DS-StyleGaussian integrates a 2D-pretrained decoder with feature Gaussian splatting and deferred stylization to achieve view-consistent zero-shot 3D style transfer from a single style image.
-
Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos
TrioMan is a tri-module data augmentation framework using a Generator for pose/camera perturbations, a Refiner with one-step diffusion, and an Examiner with dual-branch attention to improve 3D avatar learning from monocular videos, claiming better results than prior methods on two benchmarks.
-
Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM
Flow4DGS-SLAM uses optical flow to generate motion masks, initialize poses, and guide 4D Gaussian modeling with scene flow and GMM for temporal properties, claiming SOTA results in dynamic tracking and reconstruction.
-
GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction
GeoRect4D couples 3D Gaussian splatting with a single-step diffusion rectifier via degradation-aware feedback and progressive optimization to improve fidelity and consistency in sparse-view dynamic 3D reconstruction.
-
Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction
Structure-guided dynamic 3DGS methods deliver superior reconstruction fidelity and compactness on D-NeRF while gaussian-centric methods provide higher rendering speeds at the cost of quality variability and storage.