Research map / 3D vision / 3D generation
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
Nicolai Hani, Selim Engin, Jun-Jee Chao, Volkan Isler
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 transformation chains and 3D feature consistency for self-supervision (ablation) | CORN · ShapeNet v2 Car | LPIPS: 0.120 -> 0.094 | Improved |
| use transformation chains and 3D feature consistency for self-supervision (ablation) | CORN · ShapeNet v2 Chair | LPIPS: 0.245 -> 0.180 | Improved |
| add local spatial features to the global object description (ablation) | CORN · ShapeNet v2 Car | LPIPS: 0.109 -> 0.094 | Improved |
| add local spatial features to the global object description (ablation) | CORN · ShapeNet v2 Chair | LPIPS: 0.216 -> 0.180 | Improved |
| use CORN rather than SRN for single-image novel view synthesis | CORN · ShapeNet v2 Car, 108 views | LPIPS: 0.144 -> 0.103 | Improved |
| use CORN rather than SRN for single-image novel view synthesis | CORN · ShapeNet v2 Chair, 108 views | LPIPS: 0.232 -> 0.181 | Improved |
| use CORN rather than TBN | CORN · ShapeNet v2 Car | LPIPS: 0.095 -> 0.094 | Improved |
| use CORN rather than the strongest baseline | CORN · ShapeNet v2 Chair | L1: 0.092 -> 0.132 | Hurt |
| use CORN rather than the strongest baseline | CORN · ShapeNet v2 Chair | SSIM: 0.792 -> 0.722 | Hurt |
| use CORN rather than the strongest baseline | CORN · ShapeNet v2 Chair | LPIPS: 0.138 -> 0.180 | Hurt |
Closest papers by meaning
- Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis (ICCV 2021 · similarity 0.87)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.86)
- MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes (CVPR 2025 · similarity 0.86)
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image (CVPR 2024 · similarity 0.86)
- Free3D: Consistent Novel View Synthesis without 3D Representation (CVPR 2024 · similarity 0.86)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.85)
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.
