Research map / 3D vision / 3D generation
Generative View Synthesis: From Single-view Semantics to Novel-view Images
Tewodros Amberbir Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker
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 GVSNet's lifted layered semantics and appearance translation rather than the strongest SPADE-plus-NVS baseline | GVSNet · CARLA | Class Accuracy: 69.93 -> 74.34 | Improved |
| Use GVSNet rather than the strongest SPADE-plus-NVS baseline | GVSNet · Virtual-KITTI-2 | Class Accuracy: 76.81 -> 77.13 | Improved |
| Use GVSNet rather than the strongest SPADE-plus-NVS baseline | GVSNet · Cityscapes | FID: 57.15 -> 48.72 | Improved |
| Add layered, view-independent appearance translation rather than independently translating projected semantics with SPADE (ablation) | GVSNet · CARLA | FID: 68.96 -> 62.06 | Improved |
| Add the Appearance Decoder Network to decode projected high-dimensional appearance features (ablation) | SUN + LTN · CARLA | FID: 69.46 -> 62.06 | Improved |
| Add the Appearance Decoder Network to decode projected high-dimensional appearance features (ablation) | SUN + LTN · CARLA | Class Accuracy: 71.90 -> 74.34 | Improved |
Closest papers by meaning
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.90)
- Video Perception Models for 3D Scene Synthesis (NeurIPS 2025 · similarity 0.89)
- GenRec: Knowing Where to Reconstruct and Where to Generate (NeurIPS 2026 · similarity 0.89)
- HORIZON: High-Resolution Semantically Controlled Panorama Synthesis (AAAI 2024 · similarity 0.89)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.88)
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias (ICLR 2025 · similarity 0.88)
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.
