mlsanityData to 14 Oct 2026

CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction

arXiv 2606.31086 ↗First posted 30 Jun 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

The rise of home-deployed embodied AI systems is driving a growing need for fast, metric 3D reconstruction of residential spaces to support navigation, interaction, and long-horizon task execution. However, the commonly used pinhole-camera 3D reconstruction pipelines struggle to model large indoor residences efficiently due to their limited field of view, to which achieving full coverage across multiple rooms often requires thousands of images and incurs drift from long chains of incremental alignment. In this work, we present CasaMaestro (Spanish words meaning ``house'' and ``master''), a feedforward model that can take only twenty to fifty sparse multi-view indoor panoramas as input and directly predicts metric depth along with camera poses, allowing fast point-cloud reconstruction of the entire house with full coverage. CasaMaestro is the first model that supports house-scale reconstruction with multi-view panoramas. Experiments show that CasaMaestro can robustly provide high quality results in both real-world and synthetic scenes, which can serve as a strong foundation for acquiring house-scale 3D indoor assets to be applied in close-loop simulation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 48 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

14 of 48 references.

References · 14

  1. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  3. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  4. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 319
  5. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  6. 20243D Reconstruction with Spatial Memorycited by 277
  7. 2025Streaming 4D Visual Geometry Transformercited by 161
  8. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  9. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 115
  10. 2025FastVGGT: Training-Free Acceleration of Visual Geometry Transformercited by 98
  11. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
  12. 2025DA2: Depth Anything in Any Directioncited by 25
2 more
  1. 2025Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimationcited by 25
  2. 2022High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registrationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Many Eyes, One World: Feed-Forward 3D Reconstruction from Mixed Camerascited by 0