AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

TopoMA: Topology-Guided Multi-Agent Dense RGB 3D Reconstruction via Distributed Inference

Xuanxuan Zhang, ShuHui Shi, Tianxiang Zhang, Zhetao Guo, Huang Zixuan, You Li

CVPR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add topology-aware loop closure (vs no loop closure) (ablation)TopoMA · Replica apartment-00ATE (cm): 23.81 -> 10.45Improved
use topology-aware loop closure instead of MASt3R-SLAM style loop closure (ablation)TopoMA · Replica apartment-00ATE (cm): 17.94 -> 10.45Improved
use topology-aware loop closure instead of ICP submap fusion (ablation)TopoMA · Replica apartment-00ATE (cm): 15.73 -> 10.45Improved
use multiple agents with loop closure instead of a single agent (ablation)TopoMA · Replica apartment-00ATE (cm): 11.68 -> 10.45Improved
add loop closure (compute cost) (ablation)TopoMA · Replica apartment-00FPS (Hz): 7.35 -> 6.21Hurt
add topology-aware residual transport (vs fully independent agents) (ablation)TopoMA · Replica apartment-00ATE (cm): 18.34 -> 10.48Improved
use residual transport instead of centralized fusion (ablation)TopoMA · Replica apartment-00ATE (cm): 14.82 -> 10.48Improved
use residual transport instead of MNE-SLAM fusion (ablation)TopoMA · Replica apartment-00ATE (cm): 16.71 -> 10.48Improved
fuse every frame-window lightly instead of coarse fusion every 500 frames (ablation)TopoMA residual transport · Replica apartment-00ATE (cm): 12.32 -> 10.48Improved
use residual transport instead of centralized fusion (memory) (ablation)TopoMA · Replica apartment-00GPU usage (GB): 6.50 -> 5.90Improved
TopoMA vs strongest single-agent baseline on KITTI-08 and KITTI-10 sequencesTopoMA · KITTI-08 / KITTI-10RMSE ATE (m): KITTI-10: 21.57 (VGGT-Long) vs 25.20 (Ours)Hurt
TopoMA vs VGGT-Long on ScanNet reconstructionTopoMA · ScanNet (5 scenes avg)Avg. Depth L1 (cm): 60.83 -> 12.19Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy