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.
Structured3d: A large photo-realistic dataset for structured 3d modeling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
CONDITIONAL 2representative citing papers
Pre-training on physically valid but architecturally implausible synthetic floor plans substantially improves cross-domain transfer and data-efficient fine-tuning for conditioned layout generation across two model paradigms and three datasets.
citing papers explorer
-
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.
-
Mitigating Domain Shift in Conditioned Floor Plan Generation: Synthetic Pre-training for Data-Efficient Adaptation
Pre-training on physically valid but architecturally implausible synthetic floor plans substantially improves cross-domain transfer and data-efficient fine-tuning for conditioned layout generation across two model paradigms and three datasets.