Research map / Point clouds / Point cloud classification
GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding
Zijun Lin, Shuting He, Cheston Tan, Bihan Wen
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 GroundFlow to PQ3D | PQ3D · SG3D overall | task accuracy (t-acc): 25.9 -> 36.1 | Improved |
| add GroundFlow to 3D-VisTA | 3D-VisTA · SG3D overall | task accuracy (t-acc): 28.8 -> 35.1 | Improved |
| add GroundFlow to Vil3DRel | Vil3DRel · SG3D overall | task accuracy (t-acc): 28.6 -> 35.2 | Improved |
| add GroundFlow to MiKASA | MiKASA · SG3D overall | task accuracy (t-acc): 31.9 -> 34.2 | Improved |
| GroundFlow-augmented 3DVG models versus fine-tuned 3D LLM LEO | PQ3D + GroundFlow · SG3D overall | step accuracy (s-acc): 62.8 -> 64.8 | Improved |
| use GroundFlow memory fusion instead of LSTM, GRU or Transformer (ablation) | 3D-VisTA · SG3D overall | task accuracy (t-acc): 33.5 -> 35.1 | Improved |
| replace GroundFlow with GRU (ablation) | 3D-VisTA · SG3D overall | task accuracy (t-acc): +0.0 | No clear effect |
| add long-term memory on top of short-term memory (ablation) | GroundFlow on PQ3D · SG3D overall | task accuracy (t-acc): 35.7 -> 36.1 | Improved |
| add short-term memory on top of long-term memory (ablation) | GroundFlow on PQ3D · SG3D overall | task accuracy (t-acc): 34.5 -> 36.1 | Improved |
| build memory from GroundFlow outputs rather than original joint embeddings (ablation) | GroundFlow on PQ3D · SG3D overall | task accuracy (t-acc): 34.6 -> 36.1 | Improved |
| add GroundFlow to 3D-VisTA | 3D-VisTA · SG3D inference speed | inference time per step: 5.2ms -> 5.6ms | Hurt |
Closest papers by meaning
- Reasoning in Space via Grounding in the World (ICLR 2026 · similarity 0.89)
- S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance (CVPR 2026 · similarity 0.89)
- ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning (CVPR 2025 · similarity 0.88)
- CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding (ICLR 2024 · similarity 0.88)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.87)
- SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding (NeurIPS 2025 · 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.
