Research map / 3D vision / 3D generation
SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping
Yuan Shen, Wei-Chiu Ma, Shenlong Wang
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 |
|---|---|---|---|
| SGAM vs GFVS-implicit in runtime | SGAM · CLEVR-Infinite val | runtime (s/image): 33.65 -> 0.26 | Improved |
| SGAM vs GFVS-implicit on image quality | SGAM · CLEVR-Infinite val | PSNR: 23.06 -> 24.65 | Improved |
| SGAM vs GFVS-implicit on FID | SGAM · CLEVR-Infinite val | FID: 22.85 -> 21.91 | Improved |
| SGAM vs GFVS-implicit in multi-step scene FID | SGAM · CLEVR-Infinite 30x30 | FID: 16.14 -> 26.60 | Hurt |
| SGAM vs GFVS-implicit on scene-level coverage | SGAM · CLEVR-Infinite 30x30 | Cov: 0.376 -> 0.454 | Improved |
| SGAM vs GFVS-explicit under long unrolling | SGAM · CLEVR-Infinite 30x30 | FID: 82.82 -> 26.60 | Improved |
| SGAM vs InfiniteNature on real-world unrolling | SGAM · GoogleEarth-Infinite 60-step | FID: 182.6 -> 79.26 | Improved |
| SGAM vs InfiniteNature on one-step prediction | SGAM · GoogleEarth-Infinite one-step | FID: 37.92 -> 42.29 | Hurt |
| add RGBD-integration global mapping (ablation) | SGAM · GoogleEarth-Infinite unrolling | scene diversity/quality | Improved |
| add first-stage codebook training and finetune encoder (ablation) | SGAM · CLEVR-Infinite | image-level metrics | Improved |
| remove geometric grounding step in GFVS baseline | GFVS · CLEVR-Infinite | unrolling quality | Improved |
Later papers that compared with this method
2 later accepted papers report SGAM as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Compositional Generative Model of Unbounded 4D Cities (TPAMI 2025 · better on 2 of 2 shared results)
- CityDreamer: Compositional Generative Model of Unbounded 3D Cities (CVPR 2024 · better on 4 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
- 3D Scene Generation: A Survey (IJCV 2026 · similarity 0.90)
- WorldGrow: Generating Infinite 3D World (AAAI 2026 · similarity 0.89)
- WonderZoom: Multi-Scale 3D World Generation (CVPR 2026 · similarity 0.89)
- WonderWorld: Interactive 3D Scene Generation from a Single Image (CVPR 2025 · similarity 0.88)
- Video Perception Models for 3D Scene Synthesis (NeurIPS 2025 · similarity 0.87)
- WorldMem: Long-term Consistent World Simulation with Memory (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.
