Research map / 3D vision / 3D generation
Image-guided Neural Object Rendering
Justus Thies, Michael Zollhöfer, Christian Theobalt, Marc Stamminger, Matthias Nießner
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 the image-guided rendering pipeline instead of Pix2Pix | Object-specific neural rendering · Car (synthetic) | MSE: 12.62 -> 3.61 | Improved |
| Use the image-guided rendering pipeline instead of Pix2Pix | Object-specific neural rendering · Statue (synthetic) | MSE: 5.40 -> 2.38 | Improved |
| Use the image-guided rendering pipeline instead of IBR | Object-specific neural rendering · Vase (synthetic) | MSE: 17.31 -> 1.12 | Improved |
| Use the image-guided rendering pipeline instead of Pix2Pix | Object-specific neural rendering · Bust (synthetic) | MSE: 4.43 -> 1.52 | Improved |
| Use the image-guided rendering pipeline instead of IBR | Object-specific neural rendering · Globe (real) | MSE: 81.06 -> 30.38 | Improved |
| Use the image-guided rendering pipeline instead of IBR | Object-specific neural rendering · Shoe (real) | MSE: 59.47 -> 56.08 | Improved |
| Use the image-guided rendering pipeline instead of Pix2Pix | Object-specific neural rendering · Bust (real) | MSE: 45.23 -> 25.24 | Improved |
| Add EFFECTSNET to estimate and handle view-dependent effects (ablation) | Image-guided rendering pipeline · Synthetic test set | MSE: 2.6876 -> 2.3864 | Improved |
| Train Pix2Pix on pure depth maps rather than position images (ablation) | Pix2Pix · Vase (synthetic test set) | MSE: 18.66 -> 36.63 | Hurt |
Closest papers by meaning
- Neural Voxel Renderer: Learning an Accurate and Controllable Rendering Tool (CVPR 2020 · similarity 0.88)
- Visual Object Networks: Image Generation with Disentangled 3D Representations (NeurIPS 2018 · similarity 0.88)
- Transformation-Grounded Image Generation Network for Novel 3D View Synthesis (CVPR 2017 · similarity 0.88)
- Decompositional Neural Scene Reconstruction with Generative Diffusion Prior (CVPR 2025 · similarity 0.86)
- Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models (CVPR 2025 · similarity 0.86)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · 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.
