Research map / 3D vision / NeRF and radiance fields
Boosting View Synthesis With Residual Transfer
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Transfer blended residuals into NeRF rendering | NeRF · Real Forward-facing | PSNR: 26.53 -> 27.08 | Helped |
| Transfer blended residuals into NeRF rendering | NeRF · Shiny dataset | PSNR: 22.43 -> 23.22 | Helped |
| Transfer blended residuals into NeX rendering | NeX · Real Forward-facing | PSNR: 27.74 -> 28.19 | Helped |
| Transfer blended residuals into NeX rendering | NeX · Shiny dataset | PSNR: 26.74 -> 28.09 | Helped |
| Transfer blended training-view colors instead of residuals (ablation) | NeRF · Horns | PSNR: 27.68 -> 23.84 | Hurt |
| Add blended residual transfer rather than direct color transfer (ablation) | NeRF · Horns | PSNR: 27.68 -> 28.52 | Helped |
| Use 1 reference view for residual blending (ablation) | NeRF · Horns | PSNR: 27.68 -> 27.94 (+0.26) | Helped |
| Use 3 reference views for residual blending (ablation) | NeRF · Horns | PSNR: 27.68 -> 28.36 (+0.68) | Helped |
| Use 5 reference views for residual blending (ablation) | NeRF · Horns | PSNR: 27.68 -> 28.52 (+0.84) | Helped |
| Increase reference views from 5 to 10 (ablation) | NeRF residual transfer · Horns | PSNR: 28.52 -> 28.49 | Hurt |
Closest papers by meaning
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.89)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.89)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.88)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.88)
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis (NeurIPS 2026 · similarity 0.88)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · 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.