Research map / 3D vision / NeRF and radiance fields
Monocular Neural Image Based Rendering With Continuous View Control
Xu Chen, Jie Song, Otmar Hilliges
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 the transforming auto-encoder (explicit latent rotation) instead of concatenating the viewpoint (ablation) | Ours · ShapeNet car | L1 error: 0.045 -> 0.039 | Improved |
| add the transforming auto-encoder instead of concatenating the viewpoint (ablation) | Ours · ShapeNet chair | L1 error: 0.065 -> 0.056 | Improved |
| add depth-guided appearance warping instead of direct flow prediction (ablation) | Ours · ShapeNet car | L1 error: 0.052 -> 0.039 | Improved |
| add depth-guided appearance warping instead of direct flow prediction (ablation) | Ours · ShapeNet chair | L1 error: 0.066 -> 0.056 | Improved |
| add the transforming auto-encoder (ablation) | Ours · ShapeNet car | SSIM: 0.943 -> 0.949 | Improved |
| add depth-guided appearance warping (ablation) | Ours · ShapeNet car | SSIM: 0.932 -> 0.949 | Improved |
| add depth-guided warping (depth prediction before flow) (ablation) | Ours · ShapeNet car flow prediction | accuracy: 76.3% -> 85.7% | Improved |
| add the transforming auto-encoder (ablation) | Ours · ShapeNet car flow prediction | accuracy: 84.6% -> 85.7% | Improved |
| add the transforming auto-encoder (ablation) | Ours · ShapeNet car depth prediction | accuracy: 89.0% -> 91.1% | Improved |
| add the transforming auto-encoder (ablation) | Ours · ShapeNet car flow prediction | L1 error: 0.022 -> 0.021 | No clear effect |
| add the transforming auto-encoder (ablation) | Ours · ShapeNet car depth prediction | L1 error: 0.134 -> 0.132 | No clear effect |
| predict depth then project to flow instead of regressing flow directly and trained on flow baseline (Zhou et al.) | Ours (w/o depth) · ShapeNet car flow prediction | accuracy: 69.1% -> 76.3% | Improved |
Closest papers by meaning
- Global Latent Neural Rendering (CVPR 2024 · similarity 0.88)
- Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis (NeurIPS 2026 · similarity 0.87)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.87)
- Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency (CVPR 2025 · similarity 0.87)
- One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation (NeurIPS 2026 · similarity 0.87)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 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.
