Research map / 3D vision / 3D generation
PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments
David Novotny, Ben Graham, Jeremy Reizenstein
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 scene-consistent latent optimization (ablation) | PerspectiveNet · ScanNet test | LPIPS: 0.426 -> 0.422 | Improved |
| add scene-consistent latent optimization (ablation) | PerspectiveNet · SceneNet test | LPIPS: 0.442 -> 0.424 | Improved |
| add scene-consistent latent optimization (ablation) | PerspectiveNet · ScanNet test | PSNR: 13.986 -> 13.762 | No clear effect |
| add scene-consistent latent optimization (ablation) | PerspectiveNet · SceneNet test | PSNR: 16.324 -> 15.687 | Hurt |
| add scene-consistent latent optimization (ablation) | PerspectiveNet · ScanNet test | Depth delta1: 0.188 -> 0.352 | Improved |
| add scene-consistent latent optimization (ablation) | PerspectiveNet · SceneNet test | Depth delta1: 0.101 -> 0.366 | Improved |
| add scene-consistent latent optimization (ablation) | PerspectiveNet · ScanNet test | Depth L1 (m): 0.120 -> 0.115 | Improved |
| add scene-consistent latent optimization (ablation) | PerspectiveNet · SceneNet test | Depth L1 (m): 0.227 -> 0.219 | Improved |
Later papers that compared with this method
1 later accepted paper reports PerspectiveNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Holistic Pose Graph: Modeling Geometric Structure Among Objects in a Scene Using Graph Inference for 3D Object Prediction (ICCV 2021 · 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
- SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D Images (AAAI 2024 · similarity 0.88)
- RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models (CVPR 2023 · similarity 0.88)
- LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image (CVPR 2018 · similarity 0.88)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.87)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.87)
- SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors (CVPR 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.
