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.
DriveDreamer: Towards real-world-driven world models for autonomous driving
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
A unified system integrating sparse-query 3D Gaussian reconstruction with multi-stage causal video generation for autonomous driving world models.
A 3D Gaussian Splatting pipeline that uses a mask-aware one-step diffusion refiner, opacity-driven Gaussian densification, and LoRA/SDS regularization to do few-shot novel-view synthesis on unconstrained images with distractors.
EvoDriveVLA uses collaborative perception-planning distillation with self-anchor and future-aware teachers to fix perception degradation and long-term instability in driving VLA models, reaching SOTA on nuScenes and NAVSIM.
citing papers explorer
-
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.
-
Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving
A unified system integrating sparse-query 3D Gaussian reconstruction with multi-stage causal video generation for autonomous driving world models.
-
Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild
A 3D Gaussian Splatting pipeline that uses a mask-aware one-step diffusion refiner, opacity-driven Gaussian densification, and LoRA/SDS regularization to do few-shot novel-view synthesis on unconstrained images with distractors.
-
EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation
EvoDriveVLA uses collaborative perception-planning distillation with self-anchor and future-aware teachers to fix perception degradation and long-term instability in driving VLA models, reaching SOTA on nuScenes and NAVSIM.