Research map / 3D vision / Gaussian splatting
LONG3R: Long Sequence Streaming 3D Reconstruction
Zhuoguang Chen, Minghui Qin, Tianyuan Yuan, Zhe Liu, Hang Zhao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add attention-based memory gating (ablation) | LONG3R · 7Scenes | FPS: 18.0 -> 21.4 | Improved |
| add attention-based memory gating (ablation) | LONG3R · 7Scenes | accuracy error mean (cm): 2.53 -> 2.57 | No clear effect |
| add attention-based memory gating (ablation) | LONG3R · 7Scenes | completion error mean (cm): 2.12 -> 2.08 | No clear effect |
| add attention-based memory gating (ablation) | LONG3R · NRGBD | accuracy error mean (cm): 6.72 -> 6.66 | No clear effect |
| use interleaved instead of concatenated dual-source decoder (ablation) | LONG3R · Replica (100 frames) | accuracy error mean (cm): 14.83 -> 12.06 | Improved |
| use interleaved instead of concatenated dual-source decoder (ablation) | LONG3R · Replica (200 frames) | accuracy error mean (cm): 29.52 -> 13.34 | Improved |
| use interleaved instead of concatenated dual-source decoder (ablation) | LONG3R · Replica (200 frames) | completion error mean (cm): 8.88 -> 3.15 | Improved |
| add long-term 3D spatial memory (ablation) | LONG3R · Replica (200 frames) | accuracy error mean (cm): 65.75 -> 11.93 | Improved |
| add long-term 3D spatial memory (ablation) | LONG3R · 7Scenes | accuracy error mean (cm): 5.76 -> 2.57 | Improved |
| use 3D spatio-temporal memory instead of Spann3R memory (ablation) | LONG3R · Replica (200 frames) | accuracy error mean (cm): 12.41 -> 11.93 | Improved |
| use 3D spatio-temporal memory instead of Spann3R memory (ablation) | LONG3R · 7Scenes | accuracy error mean (cm): 2.64 -> 2.57 | Improved |
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.
- MV-DUSt3R — MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds (CVPR 2025) · better on 1 of 1 shared result
- DUSt3R — DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024) · better on 1 of 1 shared result
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
- Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory (NeurIPS 2025 · similarity 0.91)
- Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction (NeurIPS 2026 · similarity 0.89)
- BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates (NeurIPS 2026 · similarity 0.89)
- FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry (NeurIPS 2026 · similarity 0.88)
- Continuous 3D Perception Model with Persistent State (CVPR 2025 · similarity 0.87)
- CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction (NeurIPS 2026 · similarity 0.87)
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.
