Research map / 3D vision / Gaussian splatting
Physically Grounded Dual-Opacity Gaussian Splatting for Joint RGB-TIR Reconstruction
Jin Liu, Dabin leng, Jiagang Chen, Haodong Li, Jiguang Li, Zhao Huang, Xiaoshuai Zhang, Zhiwen Zheng, Xingru Huang, Qi Xu
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 dual-opacity rendering (ablation) | RaViGS · ThermoNeRF TIR | PSNR: 31.617 -> 32.479 | Improved |
| add dual-opacity alone to baseline (ablation) | 3DGS+IR baseline · ThermoNeRF TIR | PSNR: 30.910 -> 32.068 | Improved |
| add dual-opacity alone to baseline (ablation) | 3DGS+IR baseline · ThermoNeRF RGB | PSNR: 21.878 -> 21.358 | Hurt |
| add 3-physics factorization alone (ablation) | baseline · ThermoNeRF TIR | MAE: 0.606 -> 2.259 | Hurt |
| add full set of three components | RaViGS · ThermoNeRF TIR | MAE-ROI: 1.233 -> 1.425 | Hurt |
| add physical prior loss (ablation) | RaViGS · ThermoNeRF TIR | MAE-ROI: 1.912 -> 1.350 | Improved |
| add RGB gradient loss and guided TV without physical prior (ablation) | RaViGS · ThermoNeRF TIR | PSNR: 32.479 -> 29.661 | Hurt |
| add all four loss terms vs photometric only (ablation) | RaViGS · ThermoNeRF RGB | PSNR: 21.641 -> 22.011 | Improved |
| use RaViGS instead of OMMG | RaViGS · ThermoNeRF TIR | PSNR: 32.197 -> 32.479 | Improved |
| use RaViGS instead of 3DGS+IR | RaViGS · ThermoNeRF RGB | PSNR: 21.878 -> 22.011 | Improved |
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.
- Mip-Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 3 of 3 shared results
- Scaffold-GS — Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering (CVPR 2024) · 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
- ThermalGaussian: Thermal 3D Gaussian Splatting (ICLR 2025 · similarity 0.89)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.88)
- OMG: Opacity Matters in Material Modeling with Gaussian Splatting (ICLR 2025 · similarity 0.88)
- pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024 · similarity 0.88)
- TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering (NeurIPS 2026 · similarity 0.88)
- Fix False Transparency by Noise Guided Splatting (NeurIPS 2025 · 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.
