Research map / 3D vision / 3D generation
Scalable Spatial Memory for Scene Rendering and Navigation
Wen-Cheng Chen, Chu-Song Chen, Wei-Chen Chiu, Min-Chun Hu
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 |
|---|---|---|---|
| Use SMN instead of STR-GQN for view synthesis | Scene rendering · Rooms-Free-Camera | RMSE: 15.9±12.8 -> 16.1±13.8 | Hurt |
| Use SMN instead of STR-GQN for view synthesis | Scene rendering · Orario3d Local | RMSE: 22.5±22.0 -> 21.3±20.7 | Improved |
| Use SMN instead of STR-GQN for view synthesis | Scene rendering · Orario3d Base | RMSE: 22.8±21.5 -> 21.7±21.6 | Improved |
| Use SMN instead of STR-GQN for view synthesis | Scene rendering · Orario3d Large | RMSE: 52.1±30.8 -> 25.8±22.5 | Improved |
| Add NGU episodic intrinsic reward | DQN · Item-Collecting | score: 8.85±4.05 -> 9.15±3.42 | Improved |
| Add SMN memory entropy-gain intrinsic reward | DQN · Item-Collecting | score: 8.85±4.05 -> 9.30±3.04 | Improved |
| Use SMN memory as additional Q-network input | DQN · Item-Collecting | score: 8.85±4.05 -> 9.75±3.69 | Improved |
| Add memory entropy-gain intrinsic reward | SMN-DQN · Item-Collecting | score: 9.75±3.69 -> 11.0±3.29 | Improved |
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.
- STR-GQN — STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing (ICCV 2021) · better on 3 of 4 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
- MemoNav: Working Memory Model for Visual Navigation (CVPR 2024 · similarity 0.88)
- 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning (CVPR 2025 · similarity 0.86)
- 3D-SPATIAL MULTIMODAL MEMORY (ICLR 2025 · similarity 0.85)
- Video World Models with Long-term Spatial Memory (NeurIPS 2025 · similarity 0.85)
- Memory-based Adapters for Online 3D Scene Perception (CVPR 2024 · similarity 0.84)
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator (NeurIPS 2026 · similarity 0.84)
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.
