Research map / 3D vision / Gaussian splatting
RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction
Aymen Mir, Riza Alp Guler, Jian Wang, Peter Wonka, Bing Zhou, Gerard Pons-Moll
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 |
|---|---|---|---|
| normalize line integral by I_max (ablation) | RAGA · ScanNet++ shadow quality | SAE: 0.047 -> 0.031 | Improved |
| normalize line integral by I_max (ablation) | RAGA · ScanNet++ shadow quality | SM-IoU: 0.793 -> 0.847 | Improved |
| use exponentiated attenuation instead of linear (ablation) | RAGA · ScanNet++ shadow quality | SAE: 0.035 -> 0.031 | Improved |
| use exponentiated attenuation instead of Beer-Lambert (ablation) | RAGA · ScanNet++ shadow quality | SM-IoU: 0.819 -> 0.847 | Improved |
| add avatar proxy (ablation) | RAGA · Temporal consistency | TSC: 0.0061 -> 0.0018 | Improved |
| add canonical topology locking to proxy (ablation) | RAGA · Temporal consistency | TSC: 0.0037 -> 0.0018 | Improved |
| add isotropic regularization to proxy (ablation) | RAGA · Temporal consistency | TSC: 0.0032 -> 0.0018 | Improved |
| exact ray-Gaussian line integral vs 3DGRT modified | RAGA · ScanNet++ shadow quality | SM-IoU: 0.741 -> 0.847 | Improved |
| exact line integral vs RaySplat modified | RAGA · ScanNet++ shadow quality | BF: 0.679 -> 0.812 | Improved |
| use RAGA shadows vs no shadow | RAGA · Perceptual 2AFC | preference: 73% | Improved |
Closest papers by meaning
- SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.89)
- Hardware-Rasterized Ray-Based Gaussian Splatting (CVPR 2025 · similarity 0.88)
- Gaussian Shadow Casting for Neural Characters (CVPR 2024 · similarity 0.88)
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (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.
