Research map / 3D vision / NeRF and radiance fields
STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing
Wen-Cheng Chen, Min-Chun Hu, Chu-Song Chen
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 Spatial Transformation Routing (STR-GQN instead of GQN) | GQN · RRC | RMSE: 14.62 -> 8.52 | Improved |
| add STR | GQN · RFC | RMSE: 26.80 -> 17.01 | Improved |
| add STR | GQN · DISCO | RMSE: 32.72 -> 23.57 | Improved |
| add STR | GQN · SM7 | RMSE: 9.97 -> 10.56 | Hurt |
| add STR | GQN · ShapeNet (no stochastic unit) | cross-entropy error: 0.109 -> 0.079 | Improved |
| use STR-GQN instead of E-GQN | E-GQN · RRC | RMSE: 6.8 -> 8.52 | Hurt |
| use STR-GQN instead of GRNN under image distortion | GRNN · RRC high distortion | cross-entropy error: 0.537 -> 0.522 | Improved |
| add OCM fusion instead of Sum fusion (ablation) | STR-GQN · RRC, 8 observations | RMSE: 12.18 -> 8.40 | Improved |
| add OCM fusion instead of Sum fusion (ablation) | STR-GQN · RRC, 5 observations | RMSE: 9.02 -> 8.57 | Improved |
| add OCM fusion instead of Norm fusion (ablation) | STR-GQN · RRC, 8 observations | RMSE: 8.47 -> 8.40 | No clear effect |
| use Sum fusion with more observations than 5 (ablation) | STR-GQN · RRC | RMSE: 9.02 -> 12.18 | Hurt |
Later papers that compared with this method
2 later accepted papers report STR-GQN as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Scalable Spatial Memory for Scene Rendering and Navigation (AAAI 2023 · better on 3 of 4 shared results)
- ViewFormer: NeRF-Free Neural Rendering from Few Images Using Transformers (ECCV 2022 · 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
- Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations (CVPR 2022 · similarity 0.87)
- Global Latent Neural Rendering (CVPR 2024 · similarity 0.84)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.84)
- STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction (CVPR 2025 · similarity 0.84)
- Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis (NeurIPS 2026 · similarity 0.84)
- GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding (CVPR 2024 · similarity 0.83)
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.
