← Back to all news
arXiv AI By Junaid Ahmed Ansari, Ran Ding, Fabio Pizzati, Ivan Laptev

MessyKitchens: Contact-rich object-level 3D scene reconstruction

Read the original on arXiv AI →

MessyKitchens introduces a new dataset of cluttered real-world kitchen scenes with detailed 3D object shapes, poses, and accurate contact information. The authors extend the SAM 3D single-object reconstruction method with a Multi-Object Decoder (MOD) to jointly reconstruct entire scenes, achieving better registration accuracy and reduced inter-object penetration compared to prior work. The dataset, benchmark, code, and pretrained models will be publicly released on the project website.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Aug 28

Reconstructing Humans and Objects in Interaction using Large Reconstruction Models

The paper introduces MILO, a framework that uses Large Reconstruction Models (LRMs) to reconstruct detailed 3D human‑object interactions from a single image. By treating the LRM mesh as a geometric scaffold, MILO segments it into human and object parts, fits a parametric body model to the human component, and optionally aligns an object template to the object component. The approach achieves higher reconstruction accuracy than existing baselines across multiple benchmarks and interaction scenarios.

By Agniv Chatterjee, Georgios Pavlakos
computer-visionroboticsbenchmarks
More like this →