GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images
Overview
GATOR integrates sparse observations and infers hidden surfaces to recover textured 3D objects and their scene-relative pose. It uses RGB, target-mask, and pointmap features with cross-view reasoning and semantic conditioning for strong geometric and appearance fidelity across synthetic and real-world scenes. Project page: https://research.nvidia.com/labs/lpr/gator/
Generated from attributed reports · Updated 3 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“ose for targeted structural and texture refinement through an observation-guided edit-render-review loop. Across synthetic objects, cluttered tabletops, and indoor scenes, GATOR achieves strong geometric and appearance fidelity while recovering scene-relative pose from sparse observations. Time-budget comparisons and scene-level simulation further demonstrate the reconstruction efficiency and simulation readiness. Pr”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsGATOR: Generative and Agentic 3D Object Reconstruction From Casual Images
The method integrates sparse observations, infers hidden surfaces, and recovers textured assets and their scene-relative pose. It combines RGB, target-mask, and pointmap features with cross-view reasoning and semantic conditioning, achieving strong geometric and appearance fidelity across synthetic and real-world scenes.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).