MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometries and parameters.
hub Mixed citations
3d gaussian splatting for real-time radiance field rendering.ACM Trans
Mixed citation behavior. Most common role is background (67%).
20
Pith papers citing it
Background
67% of classified citations
hub tools
citation-role summary
background 6
method 2
baseline 1
citation-polarity summary
years
2026 20representative citing papers
InvSplat is a feed-forward multi-view model that predicts 3D Gaussians augmented with intrinsic material attributes for inverse rendering and relighting.
PREX decomposes target 4D video volumes into Preserve, Reveal, and Expand roles with a region-aware adapter on a frozen diffusion backbone, trained via proxy tasks, and introduces the PREBench benchmark to reduce region-structured editing failures.
MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
A training-free method reformulates camera control as geometric displacement fields applied via differentiable latent resampling, enabling control and bias probing in video diffusion models.
PointForward uses sparse world-space 3D queries and scene graphs to deliver consistent single-pass reconstruction of dynamic driving scenes via point-aligned representations.
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
DUST decouples pose trajectories per camera source while sharing canonical Gaussians per agent to remove cross-source gradient conflicts and ghosting caused by temporal asynchrony in 4D cooperative driving scenes.
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
NeTMY neural fields with annealed encoding, multiscale optimization, and spectrum-fidelity losses achieve superior localization and distributional accuracy in NV-center inverse sensing by using a tensor power-summed dipolar operator that exposes and mitigates center-collapse failures.
CoWorld-VLA extracts semantic, geometric, dynamic, and trajectory expert tokens from multi-source supervision and feeds them into a diffusion-based hierarchical planner, achieving competitive collision avoidance and trajectory accuracy on the NAVSIM v1 benchmark.
123D unifies eight real-world and one synthetic autonomous driving datasets into a single API using independent timestamped event streams, with tools for analysis and demonstrations of cross-dataset 3D detection transfer and RL planning.
Aes3D creates the first 3D scene aesthetic assessment dataset and a model that regresses aesthetic scores from 3DGS representations alone.
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
The Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors outperforms prior methods on dynamic benchmarks by cutting Mean Accuracy error 13.43% and raising segmentation F-measure 10.49% via three uncertainty mechanisms while keeping feed-forward speed.
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching distillation.
Introduces Orthogonal Projected Gradient (OPG) and a smoothness-based temporal regularization to restore spatial identifiability and ensure physically consistent 4D scene reconstruction for closed-loop autonomous driving simulation.
RoSplat adds alpha normalization for brightness consistency across varying input views and a 3D sampling regularizer to mitigate hole artifacts in high-resolution feed-forward Gaussian splatting.
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
A 14B-parameter mixture-of-experts world model is distilled to a four-step autoregressive generator and claimed to deliver camera-controllable video at up to 50 FPS on NPUs with 30-50% of prior inference cost.
citing papers explorer
-
A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds
MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometries and parameters.
-
InvSplat: Inverse Feed-Forward Scene Splatting
InvSplat is a feed-forward multi-view model that predicts 3D Gaussians augmented with intrinsic material attributes for inverse rendering and relighting.
-
Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioning
PREX decomposes target 4D video volumes into Preserve, Reveal, and Expand roles with a region-aware adapter on a frozen diffusion backbone, trained via proxy tasks, and introduces the PREBench benchmark to reduce region-structured editing failures.
-
The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting
MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
-
Probing into Camera Control of Video Models
A training-free method reformulates camera control as geometric displacement fields applied via differentiable latent resampling, enabling control and bias probing in video diffusion models.
-
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
PointForward uses sparse world-space 3D queries and scene graphs to deliver consistent single-pass reconstruction of dynamic driving scenes via point-aligned representations.
-
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
-
One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction
DUST decouples pose trajectories per camera source while sharing canonical Gaussians per agent to remove cross-source gradient conflicts and ghosting caused by temporal asynchrony in 4D cooperative driving scenes.
-
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
-
Neural Fields for NV-Center Inverse Sensing
NeTMY neural fields with annealed encoding, multiscale optimization, and spectrum-fidelity losses achieve superior localization and distributional accuracy in NV-center inverse sensing by using a tensor power-summed dipolar operator that exposes and mitigates center-collapse failures.
-
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
CoWorld-VLA extracts semantic, geometric, dynamic, and trajectory expert tokens from multi-source supervision and feeds them into a diffusion-based hierarchical planner, achieving competitive collision avoidance and trajectory accuracy on the NAVSIM v1 benchmark.
-
123D: Unifying Multi-Modal Autonomous Driving Data at Scale
123D unifies eight real-world and one synthetic autonomous driving datasets into a single API using independent timestamped event streams, with tools for analysis and demonstrations of cross-dataset 3D detection transfer and RL planning.
-
Aes3D: Aesthetic Assessment in 3D Gaussian Splatting
Aes3D creates the first 3D scene aesthetic assessment dataset and a model that regresses aesthetic scores from 3DGS representations alone.
-
Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
-
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
The Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors outperforms prior methods on dynamic benchmarks by cutting Mean Accuracy error 13.43% and raising segmentation F-measure 10.49% via three uncertainty mechanisms while keeping feed-forward speed.
-
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching distillation.
-
Towards Physically Consistent 4D Scene Reconstruction for Closed-loop Autonomous Driving Simulation
Introduces Orthogonal Projected Gradient (OPG) and a smoothness-based temporal regularization to restore spatial identifiability and ensure physically consistent 4D scene reconstruction for closed-loop autonomous driving simulation.
-
RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering
RoSplat adds alpha normalization for brightness consistency across varying input views and a 3D sampling regularizer to mitigate hole artifacts in high-resolution feed-forward Gaussian splatting.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
MoWorld: A Flash World Model
A 14B-parameter mixture-of-experts world model is distilled to a four-step autoregressive generator and claimed to deliver camera-controllable video at up to 50 FPS on NPUs with 30-50% of prior inference cost.