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.
hub Mixed citations
3D Gaussian Splatting for Real-Time Radiance Field Rendering, August 2023
Mixed citation behavior. Most common role is background (40%).
20
Pith papers citing it
30
external citations · Pith
Background
40% of classified citations
abstract
Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.
hub tools
citation-role summary
background 2
method 2
other 1
citation-polarity summary
years
2026 20representative citing papers
GETA-3DGS is the first automatic joint structured pruning and quantization framework for 3D Gaussian Splatting, achieving roughly 5x storage reduction on standard datasets without per-scene thresholds.
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.
A conditioning-guided constrained inversion method restricts avatar edits to a low-dimensional part-specific subspace and uses an information matrix spectrum from pipeline linearization to predict and ensure stability under sparse supervision.
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
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.
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.
Digital Cousins is a generative real-to-sim method that creates diverse high-fidelity simulation scenes from real panoramas to improve generalization in robot learning and evaluation.
Habitat-GS integrates 3D Gaussian Splatting scene rendering and Gaussian avatars into Habitat-Sim, yielding agents with stronger cross-domain generalization and effective human-aware navigation.
G-EDF-Loc models the Euclidean distance field as a block-sparse Gaussian mixture to enable real-time, gradient-based 6DoF localization that remains robust under severe odometry degradation or without IMU priors.
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
Presents a nonlinear actuator-aware safety filter using high-relative-degree collision cone exponential CBFs and a backup CBF on 3DGS, claiming 47% less jerk and 2.25x faster runtime than prior 3DGS filters.
SparseStreet applies node-based learnable pruning followed by static background compression to 3D Gaussian Splatting, reporting up to 80% reduction in primitives with minimal quality loss on Waymo and nuScenes street scene data.
WebSpline uses learnable cubic Hermite splines guided by a Structural Proxy Graph to deliver state-of-the-art quality dynamic 3D Gaussian rendering from monocular videos at over 10x the speed of prior methods on iPhone and NVIDIA benchmarks.
Embodied AI requires query-conditioned world models that select the simplest physical abstraction sufficient to answer intervention queries.
SpatialPrompt turns spatial sketches and voice prompts into executable constraints for controllable AI 3D generation in XR, enabling iterative collaborative creation with color-coded contributions.
A unified training framework for mesh-based ML surrogates in CFD improves accuracy and long-horizon stability by enforcing spatial derivative consistency via multi-node prediction, using temporal cross-attention correction, and adding 3D rotary positional embeddings.
Comparative benchmark of geometric deep learning models on 3D Gaussian Splatting representations for scene classification via end-to-end training, linear probing, and clustering.
A literature survey that compiles ten years of 3D scene completion research, builds a taxonomy of representation paradigms, and outlines a future research agenda.
citing papers explorer
-
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.
-
GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting
GETA-3DGS is the first automatic joint structured pruning and quantization framework for 3D Gaussian Splatting, achieving roughly 5x storage reduction on standard datasets without per-scene thresholds.
-
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.
-
Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision
A conditioning-guided constrained inversion method restricts avatar edits to a low-dimensional part-specific subspace and uses an information matrix spectrum from pipeline linearization to predict and ensure stability under sparse supervision.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
-
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.
-
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.
-
From Seeing to Simulating: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation
Digital Cousins is a generative real-to-sim method that creates diverse high-fidelity simulation scenes from real panoramas to improve generalization in robot learning and evaluation.
-
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
Habitat-GS integrates 3D Gaussian Splatting scene rendering and Gaussian avatars into Habitat-Sim, yielding agents with stronger cross-domain generalization and effective human-aware navigation.
-
G-EDF-Loc: 3D Continuous Gaussian Distance Field for Robust Gradient-Based 6DoF Localization
G-EDF-Loc models the Euclidean distance field as a block-sparse Gaussian mixture to enable real-time, gradient-based 6DoF localization that remains robust under severe odometry degradation or without IMU priors.
-
TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
-
FastBridge: Closing the Model-Based Realization Gap in Safety Filters on 3D Gaussian Splatting for Fast Quadrotor Flight
Presents a nonlinear actuator-aware safety filter using high-relative-degree collision cone exponential CBFs and a backup CBF on 3DGS, claiming 47% less jerk and 2.25x faster runtime than prior 3DGS filters.
-
SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation
SparseStreet applies node-based learnable pruning followed by static background compression to 3D Gaussian Splatting, reporting up to 80% reduction in primitives with minimal quality loss on Waymo and nuScenes street scene data.
-
WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos
WebSpline uses learnable cubic Hermite splines guided by a Structural Proxy Graph to deliver state-of-the-art quality dynamic 3D Gaussian rendering from monocular videos at over 10x the speed of prior methods on iPhone and NVIDIA benchmarks.
-
Physically Viable World Models: A Case for Query-Conditioned Embodied AI
Embodied AI requires query-conditioned world models that select the simplest physical abstraction sufficient to answer intervention queries.
-
SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design
SpatialPrompt turns spatial sketches and voice prompts into executable constraints for controllable AI 3D generation in XR, enabling iterative collaborative creation with color-coded contributions.
-
Mesh Based Simulations with Spatial and Temporal awareness
A unified training framework for mesh-based ML surrogates in CFD improves accuracy and long-horizon stability by enforcing spatial derivative consistency via multi-node prediction, using temporal cross-attention correction, and adding 3D rotary positional embeddings.
-
Learning Representations from 3D Gaussian Splats
Comparative benchmark of geometric deep learning models on 3D Gaussian Splatting representations for scene classification via end-to-end training, linear probing, and clustering.
-
Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms
A literature survey that compiles ten years of 3D scene completion research, builds a taxonomy of representation paradigms, and outlines a future research agenda.
- EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI