A component-aware style transfer framework for satellite sim-to-real reduces distribution gap to FID 54.32 and raises GDRNet pose AUC to 0.611 by injecting part-wise real style codes with consistency losses.
Domain randomization for transferring deep neural networks from sim- ulation to the real world
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
E2E-Fly supplies an end-to-end training, validation, and deployment stack that lets researchers train differentiable-physics-based policies for six quadrotor tasks and transfer them directly to two physical platforms.
citing papers explorer
-
Component-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data Construction
A component-aware style transfer framework for satellite sim-to-real reduces distribution gap to FID 54.32 and raises GDRNet pose AUC to 0.611 by injecting part-wise real style codes with consistency losses.
-
E2E-Fly: An Integrated Training-to-Deployment System for End-to-End Quadrotor Autonomy
E2E-Fly supplies an end-to-end training, validation, and deployment stack that lets researchers train differentiable-physics-based policies for six quadrotor tasks and transfer them directly to two physical platforms.
- Do We Really Need Immediate Resets? Rethinking Collision Handling for Efficient Robot Navigation