Slot3R: Set-Associative Spatial Memory for Streaming 3D Reconstruction

Key points

• Spatial memory is a natural fit because it organizes history by reconstructed 3D location.1
• Yet Point3R uses spatial proximity both to associate a new observation with an existing memory entry and to decide whether to fuse it, conflating co-location with state identity.1
• A bounded sparse readout further decouples persistent storage from per-frame decoder access.1
• At 300-500 sampled frames, Slot3R reduces Point3R's point-cloud accuracy error (Acc) by 57.1%-63.1% on 7Scenes and 64.0%-72.0% on NeuralRGBD, lowers Sim(3)-aligned absolute trajectory error (ATE) on all three pose benchmarks, and remains competitive on video-depth estimation.1

Sources (1)

• [1]Slot3R: Set-Associative Spatial Memory for Streaming 3D Reconstruction
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 04:39 PM

  Streaming 3D reconstruction must preserve evidence from each frame while processing an expanding scene online.

  Spatial memory is a natural fit because it organizes history by reconstructed 3D location.

Extractive summary: sentences quoted from the sources.