Research map / 3D vision / NeRF and radiance fields
RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes
Jiarui Zhang, Zhihao Li, Chong Wang, Bihan Wen
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 occupancy sparsity loss L_p (ablation) | RF4D · Oxford RobotCar Scene 1 | CD: 80.9668 -> 9.2251 | Improved |
| add occupancy sparsity loss L_p (ablation) | RF4D · Oxford RobotCar Scene 1 | SSIM: 0.3184 -> 0.5662 | Improved |
| add temporal consistency loss L_oc with scene flow, without motion regularization (ablation) | RF4D · Boreas Sun | PSNR: 25.28 -> 23.96 | Hurt |
| add temporal consistency loss L_oc with scene flow, without motion regularization (ablation) | RF4D · Boreas Snow | PSNR: 27.52 -> 23.43 | Hurt |
| add temporal consistency loss L_oc on top of L_p (ablation) | RF4D · Oxford RobotCar Scene 1 | CD: 9.2251 -> 7.5713 | Improved |
| add motion offset regularization L_m on top of L_p and L_oc (ablation) | RF4D · Boreas Sun | PSNR: 23.96 -> 26.65 | Improved |
| add motion offset regularization L_m on top of L_p and L_oc (ablation) | RF4D · Oxford RobotCar Scene 3 | CD: 5.1028 -> 3.2896 | Improved |
| add temporal modeling and scene flow vs static Radar Fields | RF4D · Boreas Sun | SSIM: 0.3641 -> 0.7001 | Improved |
| RF4D vs Radar Fields on PSNR in two Oxford scenes | RF4D · Oxford RobotCar Scene 3 | PSNR: 24.02 -> 23.76 | Hurt |
| learn occupancy without external estimator vs CFAR/Bayesian supervision | RF4D · Oxford RobotCar Scene 1 | CD: 13.2786 -> 7.3449 | Improved |
| RF4D vs Bayesian filtering for occupancy on rain scene | RF4D · Boreas Rain | CD: 8.6918 -> 10.4558 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Hexplane — HexPlane: A Fast Representation for Dynamic Scenes (CVPR 2023) · better on 1 of 1 shared result
- D-NeRF — D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021) · better on 1 of 1 shared result
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
- Dynamic 3D Gaussian Fields for Urban Areas (NeurIPS 2024 · similarity 0.87)
- Multi-Level Neural Scene Graphs for Dynamic Urban Environments (CVPR 2024 · similarity 0.87)
- LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis (CVPR 2024 · similarity 0.86)
- Swift-Mapping: Online Neural Implicit Dense Mapping in Urban Scenes (AAAI 2024 · similarity 0.86)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.86)
- Flux4D: Flow-based Unsupervised 4D Reconstruction (NeurIPS 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.
