Research map / 3D vision / Gaussian splatting
BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
David Svitov, Pietro Morerio, Lourdes Agapito, Alessio Del Bue
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 RGB texture to billboards (ablation) | BBSplat · Tanks&Temples ablation | PSNR: 25.17 -> 25.68 | Improved |
| add learnable alpha texture to billboards (ablation) | BBSplat · Tanks&Temples ablation | LPIPS: 0.1858 -> 0.1649 | Improved |
| add texture regularization L_texture (ablation) | BBSplat · Tanks&Temples ablation | Storage: 131 MB -> 93 MB | Improved |
| add texture regularization L_texture (ablation) | BBSplat · Tanks&Temples ablation | PSNR: 25.54 -> 25.68 | Mixed |
| add quantization and ZIP compression of textures (ablation) | BBSplat · Tanks&Temples ablation | Storage: 662 MB -> 93 MB | Improved |
| add quantization and ZIP compression of textures (ablation) | BBSplat · Tanks&Temples ablation | PSNR: 25.71 -> 25.68 | Hurt |
| use BBSplat textured primitives instead of Gaussians under fixed storage | 3DGS-MCMC baseline · DTU fixed storage | LPIPS: 0.3282 -> 0.2770 | Improved |
| use BBSplat at large primitive counts on outdoor Mip-NeRF-360 | 3DGS-MCMC baseline · Mip-NeRF-360 large primitive count | PSNR: 29.52 -> 28.33 | Hurt |
| use BBSplat instead of 2DGS for mesh extraction | DTU mesh extraction · DTU | Chamfer distance: 0.80 -> 0.91 | Hurt |
| use 64x64 textures with fewer primitives at fixed parameter budget (ablation) | BBSplat · Tanks&Temples Truck | PSNR: 25.99 -> 23.34 | Hurt |
| use 8x8 textures instead of 16x16 (ablation) | BBSplat · Tanks&Temples Truck | Size (MB): 102 -> 207 | Hurt |
| increase regularization threshold sigma from 10 to 1500 (ablation) | BBSplat · Tanks&Temples Truck | Size (MB): 139 -> 87 | Improved |
Closest papers by meaning
- Anti-Aliased 2D Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.88)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.88)
- FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes (NeurIPS 2024 · similarity 0.88)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (CVPR 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.
