Research map / 3D vision / NeRF and radiance fields
DINER: Depth-Aware Image-Based NEural Radiance Fields
Malte Prinzler, Otmar Hilliges, Justus Thies
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 DINER instead of pixelNeRF | Image-based NeRF · FaceScape | LPIPS: 0.165 -> 0.099 | Improved |
| Use DINER instead of pixelNeRF | Image-based NeRF · DTU | LPIPS: 0.38 -> 0.23 | Improved |
| Add depth awareness (ablation) | pixelNeRF · FaceScape | LPIPS: 0.16 -> 0.15 | Improved |
| Add perceptual loss (ablation) | Depth-aware pixelNeRF · FaceScape | LPIPS: 0.15 -> 0.11 | Improved |
| Add perceptual loss (ablation) | DINER · FaceScape | PSNR: 24.40 -> 22.42 | Hurt |
| Add source feature extrapolation (ablation) | DINER with perceptual loss · FaceScape | LPIPS: 0.11 -> 0.11 | No clear effect |
| Add anti-bias loss (ablation) | DINER with source feature extrapolation · FaceScape | L1: 0.029 -> 0.022 | Improved |
| Add depth-guided sampling (ablation) | DINER with anti-bias loss · FaceScape | LPIPS: 0.11 -> 0.12 | Hurt |
| Increase batch size after reducing samples per ray with depth-guided sampling (ablation) | DINER · FaceScape | LPIPS: 0.12 -> 0.10 | Improved |
| Improve depth accuracy (ablation) | DINER · FaceScape | Synthesis quality | Improved |
| Use depth-guided instead of coarse-to-fine sampling with 40 samples per ray (ablation) | DINER sampling · FaceScape | Median Chamfer distance: 6.4 mm -> 0.28 mm | Improved |
| Add perceptual loss (ablation) | DINER · DTU | LPIPS: 0.27 -> 0.23 | Improved |
Later papers that compared with this method
2 later accepted papers report DINER as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Split-Layer: Enhancing Implicit Neural Representation by Maximizing the Dimensionality of Feature Space (AAAI 2026 · better on 1 of 1 shared result)
- V2V3D: View-to-View Denoised 3D Reconstruction for Light Field Microscopy (CVPR 2025 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ECCV 2020 · similarity 0.89)
- Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes (CVPR 2021 · similarity 0.89)
- GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis (NeurIPS 2020 · similarity 0.88)
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs (CVPR 2022 · similarity 0.88)
- DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth Adaptation (NeurIPS 2023 · similarity 0.87)
- AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization (AAAI 2024 · 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.
