Newest papers

SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images

Rundong Luo, Yunong Liu, Di Cao, Matthew Tancik, Shyamal Buch, Colton Stearns, Wenqi Xian · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28585 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La simulación de confianza es una poderosa herramienta para la robótica, pero la construcción de escenas diversas, preparadas para la simulación a escala sigue siendo difícil. Reconstruir escenas a partir de imágenes únicas es una alternativa prometedora, pero la similitud visual por sí sola es insuficiente: los objetos también deben ser recuperados, colocados con precisión y aterrizados físicamente. Los métodos existentes que se basan en la física post-hoc a menudo desplazan objetos, produciendo escenas que parecen correctas pero se comportan mal bajo manipulación. Presentamos SceneRig, un sistema de agentes que convierte una imagen única en una escena editable, preparada para la simulación. SceneRig combina herramientas geométricas, visuales y físicas para reconstruir una escena 3D fiel. Un agente luego realiza loop

Machine translation (Meta M2M100); the English original follows.

Abstract

Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from single images is a promising alternative, but visual similarity alone is insufficient: objects must also be recovered, accurately placed, and physically grounded. Existing methods that rely on post-hoc physics settling often misplace objects, producing scenes that look correct but behave poorly under manipulation. We present SceneRig, an agentic system that turns a single image into an editable, simulation-ready scene. SceneRig combines geometric, visual, and physical tools to reconstruct a faithful 3D scene. An agent then performs edit-and-validate loops inside a physics simulator to achieve physical stability. Across diverse inputs, SceneRig improves instance segmentation, object-centric appearance, and 3D placement while keeping the reconstructed scenes physically stable. Furthermore, SceneRig is effective for downstream robotics: its scenes predict real-robot policy outcomes more accurately than the baseline method and more reliably support replay of recorded manipulations without trajectory adaptation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer vision, Artificial intelligence, Computer science, Trajectory, Scale (ratio), Similarity (geometry)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange