Research map / 3D vision / Gaussian splatting
Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting
Kaiqiang Xiong, Rui Peng, Jiahao Wu, Zhanke Wang, Jie Liang, Xiaoyun Zheng, Feng Gao, Ronggang Wang
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 feature-based top-k multi-view photometric consistency loss (ablation) | ICO-GS · LLFF (3-view) | PSNR: 21.82 -> 22.20 | Improved |
| add feature-based top-k multi-view photometric consistency loss (ablation) | ICO-GS · DTU (3-view) | PSNR: 21.31 -> 21.77 | Improved |
| add edge-aware depth smoothness loss (ablation) | ICO-GS · LLFF (3-view) | PSNR: 22.16 -> 22.20 | Improved |
| add edge-aware depth smoothness loss (ablation) | ICO-GS · DTU (3-view) | PSNR: 21.67 -> 21.77 | Improved |
| add cycle consistency depth filtering (ablation) | ICO-GS · LLFF (3-view) | PSNR: 21.86 -> 22.20 | Improved |
| add cycle consistency depth filtering (ablation) | ICO-GS · DTU (3-view) | PSNR: 21.25 -> 21.77 | Improved |
| add virtual-view photometric consistency loss (ablation) | ICO-GS · LLFF (3-view) | PSNR: 21.79 -> 22.20 | Improved |
| add virtual-view photometric consistency loss (ablation) | ICO-GS · DTU (3-view) | PSNR: 21.20 -> 21.77 | Improved |
| add all ICO-GS components on top of BinocularGS | ICO-GS · LLFF (3-view) | PSNR: 21.44 -> 22.20 | Improved |
| add all ICO-GS components on top of BinocularGS | ICO-GS · DTU (3-view) | PSNR: 20.71 -> 21.77 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- NexusGS — NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting (CVPR 2025) · better on 1 of 3 shared results
- CoR-GS — CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization (ECCV 2024) · better on 2 of 2 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
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.91)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild (NeurIPS 2025 · similarity 0.90)
- Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization (CVPR 2025 · similarity 0.89)
- Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity (AAAI 2025 · similarity 0.89)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (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.
