CARLA-GS is a modular pipeline that uses an LLM for semantic trajectory planning, CARLA for physics execution, and 3D Gaussian Splatting for photorealistic rendering to synthesize autonomous driving corner cases.
4d gaussian splatting for real-time dynamic scene rendering
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
GaussianMap learns adaptive Gaussian primitives on the BEV plane from multi-sensor data to produce vectorized HD maps, reporting state-of-the-art results on nuScenes and Argoverse 2.
SemDynReg constructs per-object ID maps from SAM and image features to regularize position, scale, and rotation of top-k Gaussians per object in dynamic 3DGS.
Real2Sim reconstructs editable dynamic driving scenes as temporally continuous Gaussians integrated with a differentiable MPM physics solver for high-fidelity simulation of interactions and collisions.
GA-GS uses motion segmentation, diffusion-based inpainting for pseudo-ground-truth, and per-Gaussian authenticity scalars to achieve SOTA static scene reconstruction from videos with dynamic occlusions.
Ground4D reconstructs dynamic 4D scenes from monocular video by initializing dynamic Gaussians from VGGT geometry and refining them with multi-view depth consistency at observed and virtual viewpoints.
citing papers explorer
-
CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis
CARLA-GS is a modular pipeline that uses an LLM for semantic trajectory planning, CARLA for physics execution, and 3D Gaussian Splatting for photorealistic rendering to synthesize autonomous driving corner cases.
-
GaussianMap: Learning Gaussian Representation for Multi-Sensor Online HD Map Construction
GaussianMap learns adaptive Gaussian primitives on the BEV plane from multi-sensor data to produce vectorized HD maps, reporting state-of-the-art results on nuScenes and Argoverse 2.
-
SemDynReg: Semantics-Guided Deformation Regularization for Dynamic 3D Gaussian Splatting
SemDynReg constructs per-object ID maps from SAM and image features to regularize position, scale, and rotation of top-k Gaussians per object in dynamic 3DGS.
-
Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
Real2Sim reconstructs editable dynamic driving scenes as temporally continuous Gaussians integrated with a differentiable MPM physics solver for high-fidelity simulation of interactions and collisions.
-
GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction
GA-GS uses motion segmentation, diffusion-based inpainting for pseudo-ground-truth, and per-Gaussian authenticity scalars to achieve SOTA static scene reconstruction from videos with dynamic occlusions.
-
Ground4D: Consistency-Aware 4D Reconstruction from Monocular Video
Ground4D reconstructs dynamic 4D scenes from monocular video by initializing dynamic Gaussians from VGGT geometry and refining them with multi-view depth consistency at observed and virtual viewpoints.