Research map / 3D vision / Gaussian splatting
AVSplat:Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning
MUYU XU, Fangneng Zhan, Yu Wei, Hanspeter Pfister, Shijian Lu
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-guided Voxel Fusion to baseline (ablation) | AnySplat baseline · DL3DV (64 input views) | PSNR: 21.14 -> 21.57 | Improved |
| add Assist View Preconditioning on top of fusion (ablation) | AVSplat · DL3DV (64 input views) | PSNR: 21.57 -> 21.67 | Improved |
| add Assist View Preconditioning on top of fusion (ablation) | AVSplat · DL3DV (64 input views) | SSIM: 0.692 -> 0.717 | Improved |
| AVSplat vs AnySplat on highly overlapping ACID at 72 views | AnySplat · ACID (72 input views) | PSNR: 22.45 -> 23.24 | Improved |
| AVSplat vs AnySplat at 64 views | AnySplat · DL3DV (64 input views) | PSNR: 21.14 -> 21.67 | Improved |
| add assist view preconditioning (attention concentration) | AVSplat · DL3DV (16 input views) | GeoMass@1patch: 0.286 -> 0.374 | Improved |
| add assist view preconditioning (attention entropy) | AVSplat · DL3DV (16 input views) | attention entropy: 0.693 -> 0.642 | Improved |
| AVSplat in sparse views (assist disabled) vs AnySplat | AnySplat · DL3DV (3 input views) | PSNR: 15.04 -> 14.41 | Hurt |
| AVSplat vs AnySplat at 16 views | AnySplat · Mip-NeRF 360 (16 input views) | PSNR: 17.81 -> 18.13 | Mixed |
| AVSplat vs AnySplat at 48 views | AnySplat · Mip-NeRF 360 (48 input views) | PSNR: 19.40 -> 19.30 | Hurt |
Closest papers by meaning
- FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes (NeurIPS 2024 · similarity 0.90)
- MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024 · similarity 0.90)
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.90)
- MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models (CVPR 2025 · similarity 0.89)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.89)
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.
