AutoScale is a closed-loop data engine using Graph-RAE for scene representation and Cluster-GA for importance-based retrieval to improve real-synthetic co-training for autonomous driving.
Mtgs: Multi-traversal gaussian splatting
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
fields
cs.CV 7representative citing papers
ADM-GS decomposes static background appearance into traversal-invariant material and traversal-dependent illumination via a frequency-separated neural light field, yielding +0.98 dB PSNR gains and better cross-traversal consistency on Argoverse 2 and Waymo data.
P2GS jointly decomposes LDR images into a view-invariant linear HDR radiance field, per-view exposure scales, and tone-mapping functions without HDR supervision to enforce photometric consistency in urban Gaussian Splatting.
Reducing expert-student asymmetries in visibility, uncertainty, and route specification enables a new TransFuser v6 policy that reaches 95 DS on Bench2Drive and more than doubles prior scores on Longest6 v2 and Town13.
OMEGA guides diffusion sampling with per-step constrained optimization and game-theoretic adversarial modeling to generate physically valid and interactive driving scenes, raising valid scene ratios from 32% to 72% and producing 5x more near-collisions.
SimScale synthesizes unseen driving states from real logs via neural rendering and reactive environments, generates pseudo-expert trajectories, and shows that co-training on real plus simulated data improves planning robustness and generalization on real benchmarks, with gains scaling by 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.
citing papers explorer
-
Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
AutoScale is a closed-loop data engine using Graph-RAE for scene representation and Cluster-GA for importance-based retrieval to improve real-synthetic co-training for autonomous driving.
-
Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction
ADM-GS decomposes static background appearance into traversal-invariant material and traversal-dependent illumination via a frequency-separated neural light field, yielding +0.98 dB PSNR gains and better cross-traversal consistency on Argoverse 2 and Waymo data.
-
P2GS: Physical Prior-guided Gaussian Splatting for Photometrically Consistent Urban Reconstruction
P2GS jointly decomposes LDR images into a view-invariant linear HDR radiance field, per-view exposure scales, and tone-mapping functions without HDR supervision to enforce photometric consistency in urban Gaussian Splatting.
-
LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
Reducing expert-student asymmetries in visibility, uncertainty, and route specification enables a new TransFuser v6 policy that reaches 95 DS on Bench2Drive and more than doubles prior scores on Longest6 v2 and Town13.
-
Optimization-Guided Diffusion for Interactive Scene Generation
OMEGA guides diffusion sampling with per-step constrained optimization and game-theoretic adversarial modeling to generate physically valid and interactive driving scenes, raising valid scene ratios from 32% to 72% and producing 5x more near-collisions.
-
SimScale: Learning to Drive via Real-World Simulation at Scale
SimScale synthesizes unseen driving states from real logs via neural rendering and reactive environments, generates pseudo-expert trajectories, and shows that co-training on real plus simulated data improves planning robustness and generalization on real benchmarks, with gains scaling by simulation
-
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.