AI Paper Atlas

Research map / 3D vision / Gaussian splatting

LONG3R: Long Sequence Streaming 3D Reconstruction

Zhuoguang Chen, Minghui Qin, Tianyuan Yuan, Zhe Liu, Hang Zhao

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 25 citations (OpenAlex)

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 attention-based memory gating (ablation)LONG3R · 7ScenesFPS: 18.0 -> 21.4Improved
add attention-based memory gating (ablation)LONG3R · 7Scenesaccuracy error mean (cm): 2.53 -> 2.57No clear effect
add attention-based memory gating (ablation)LONG3R · 7Scenescompletion error mean (cm): 2.12 -> 2.08No clear effect
add attention-based memory gating (ablation)LONG3R · NRGBDaccuracy error mean (cm): 6.72 -> 6.66No clear effect
use interleaved instead of concatenated dual-source decoder (ablation)LONG3R · Replica (100 frames)accuracy error mean (cm): 14.83 -> 12.06Improved
use interleaved instead of concatenated dual-source decoder (ablation)LONG3R · Replica (200 frames)accuracy error mean (cm): 29.52 -> 13.34Improved
use interleaved instead of concatenated dual-source decoder (ablation)LONG3R · Replica (200 frames)completion error mean (cm): 8.88 -> 3.15Improved
add long-term 3D spatial memory (ablation)LONG3R · Replica (200 frames)accuracy error mean (cm): 65.75 -> 11.93Improved
add long-term 3D spatial memory (ablation)LONG3R · 7Scenesaccuracy error mean (cm): 5.76 -> 2.57Improved
use 3D spatio-temporal memory instead of Spann3R memory (ablation)LONG3R · Replica (200 frames)accuracy error mean (cm): 12.41 -> 11.93Improved
use 3D spatio-temporal memory instead of Spann3R memory (ablation)LONG3R · 7Scenesaccuracy error mean (cm): 2.64 -> 2.57Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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