Research map / Point clouds / Segmentation and detection
MORE-STEM: Long-Short MemOry REcall and Spatio-TEmporal Consistency Model for Query-Driven 3D/4D Point Cloud Segmentation
Chade Li, Haida Feng, Pengju Zhang, Yihong Wu
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 Cross-Frame Text-Visual Alignment (CFTVA) (ablation) | MORE-STEM · Instruct3D | mIoU: 29.7 -> 31.4 | Improved |
| add Spatio-Temporal Consistency Model (STEM) (ablation) | MORE-STEM · Instruct3D | mIoU: 30.6 -> 31.4 | Improved |
| add Long-Term Memory (LTM) (ablation) | MORE-STEM · Instruct3D | mIoU: 30.3 -> 31.4 | Improved |
| add Short-Term Memory (STM) (ablation) | MORE-STEM · Instruct3D | mIoU: 30.8 -> 31.4 | Improved |
| add all four modules to baseline (ablation) | baseline · Instruct3D | mIoU: 28.8 -> 31.4 | Improved |
| use MORE-STEM instead of 3D-STMN for instruction segmentation | 3D-STMN · InstructKITTI 3D | Acc: 14.70 -> 38.62; latency 0.05 -> 0.19 s; GPU 13.2 -> 28.9 | Improved |
| use MORE-STEM vs RefMask3D on ScanRefer | RefMask3D · ScanRefer | mIoU: 44.8 -> 52.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- SegPoint — SegPoint: Segment Any Point Cloud via Large Language Model (ECCV 2024) · better on 2 of 2 shared results
- MR-COSMO — MR-COSMO: Visual-Text Memory Recall and Direct CrOSs-MOdal Alignment Method for Query-Driven 3D Segmentation (AAAI 2026) · better on 1 of 1 shared result
- FEAST-Mamba — FEAST-Mamba: FEAture and SpaTial Aware Mamba Network with Bidirectional Orthogonal Fusion for Cross-Modal Point Cloud Segmentation (AAAI 2025) · 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
- More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding (AAAI 2025 · similarity 0.88)
- Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding (CVPR 2025 · similarity 0.86)
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction (CVPR 2026 · similarity 0.86)
- MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation (NeurIPS 2025 · similarity 0.86)
- SceneForge: Enhancing 3D-text alignment with Structured Scene Compositions (NeurIPS 2025 · similarity 0.86)
- X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer (AAAI 2024 · similarity 0.86)
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.
