Research map / 3D vision / Gaussian splatting
DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting
Qian Wang, Yu Wang, Weiqi Li, Xinhua Cheng, Xiandong MENG, Ronggang Wang, Jian Zhang
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 progressive sampling and filtering (PSF) (ablation) | DualDiff3D · LLFF ablation setting | PSNR: 15.43 -> 15.71 | Improved |
| add confidence-driven weighting (CDW) (ablation) | DualDiff3D · LLFF ablation setting | PSNR: 15.43 -> 16.04 | Improved |
| add both PSF and CDW (ablation) | DualDiff3D · LLFF ablation setting | PSNR: 15.43 -> 16.34 | Improved |
| use DualDiff refiner instead of DIFIX (ablation) | DualDiff3D · LLFF ablation setting | PSNR: 15.21 -> 15.43 | Improved |
| add full CDW to no-CDW (ablation) | DualDiff3D · LLFF ablation setting (CDW terms) | PSNR: 19.97 -> 20.35 | Improved |
| add only the projection confidence term (ablation) | DualDiff3D · LLFF ablation setting (CDW terms) | PSNR: 19.97 -> 20.26 | Improved |
| combine all three CDW terms instead of C_proj alone (ablation) | DualDiff3D · LLFF ablation setting (CDW terms) | SSIM: 0.6612 -> 0.6709 | Improved |
| use K=3 refinement steps instead of K=2 (ablation) | DualDiff3D · LLFF ablation setting (CDW terms) | PSNR: 20.26 -> 20.35 | Improved |
| use K=4 instead of K=3 (ablation) | DualDiff3D · LLFF ablation setting (CDW terms) | PSNR: 20.35 -> 20.37 | No clear effect |
| train refiner on multiple view counts (DualDiff-m) vs only 24-view (DualDiff-s) | DualDiff · DL3DV refinement, 3-View | PSNR: 13.49 -> 13.89 | Improved |
| use DualDiff refinement instead of DIFIX refinement | 3DGS · DL3DV refinement, 3-View | PSNR: 13.11 -> 13.89 | Improved |
| DualDiff3D vs GSFixer on Mip-NeRF360 6-view | DualDiff3D · Mip-NeRF360, 6-View | PSNR: 17.27 -> 17.22 | No clear effect |
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.
- GSFixer — GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors (ICML 2026) · better on 1 of 1 shared result
- GenFusion — GenFusion: Closing the Loop between Reconstruction and Generation via Videos (CVPR 2025) · better on 1 of 1 shared result
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
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models (CVPR 2025 · similarity 0.90)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.89)
- DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation (ICLR 2025 · similarity 0.89)
- SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D (ICLR 2024 · similarity 0.89)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · 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.
