Research map / 3D vision / Depth and stereo
Rascene: High-Fidelity 3D Scene Imaging with mmWave Communication Signals
Kunzhe Song, Geo Jie Zhou, Xiaoming Liu, Huacheng Zeng
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 |
|---|---|---|---|
| fuse 5 radio frames instead of 1 (ablation) | Rascene · within-dataset test | AbsRel: 14.1% -> 9.4% | Improved |
| fuse 5 radio frames instead of 1 (ablation) | Rascene · within-dataset test | Chamfer distance (cm): 31.6 -> 19.7 | Improved |
| add a second frame to fusion (1 -> 2) (ablation) | Rascene · within-dataset test | AbsRel: 14.1% -> 11.1% | Improved |
| add rotation errors (0-5 deg to 10-15 deg) to poses at test time (ablation) | Rascene · pose robustness | AbsRel: 11.7% -> 18.8% | Hurt |
| add translation errors up to 15 cm to poses at test time (ablation) | Rascene · pose robustness | AbsRel: 9.4% -> 9.5% | No clear effect |
| place paper sheet or styrofoam occluder in front of device | Rascene · occlusion test | AbsRel: 5.6% -> 6.1% (paper), 6.4% (styrofoam) | No clear effect |
| use multi-frame instead of single-frame inference at long range (ablation) | Rascene · range 3 to 6 m | mean absolute error (cm) at 6 m: 41 -> 24 | Improved |
| use Rascene 1-frame instead of PanoRadar 1-frame | RF 3D imaging baselines · within-dataset test | AbsRel: 14.7% -> 14.1% | No clear effect |
| use Rascene 5-frame instead of CartoRadar 5-frame | RF 3D imaging baselines · within-dataset test | Chamfer distance (cm): 26.8 -> 19.7 | Improved |
Closest papers by meaning
- RaLD: Generating High-Resolution 3D Radar Point Clouds with Latent Diffusion (AAAI 2026 · similarity 0.85)
- RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis (NeurIPS 2026 · similarity 0.84)
- RPGFusion: 4D Radar Prior-Guided Multi-Modal Fusion for 3D Detection (CVPR 2026 · similarity 0.83)
- RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving (AAAI 2026 · similarity 0.83)
- 3D Point Splatting for mmWave Radar Novel View Synthesis (NeurIPS 2026 · similarity 0.82)
- HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection (AAAI 2025 · similarity 0.81)
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.
