Research map / 3D vision / Gaussian splatting
OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS
Han Ling, Xian Xu, Yinghui Sun, Quansen Sun
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 residual R to uncertainty beta (hybrid assessment) (ablation) | OCSplats · Ablation mean (Statue, Fountain, Spot) | PSNR: 23.04 -> 24.17 | Improved |
| add uncertainty beta to residual R (hybrid assessment) (ablation) | OCSplats · Ablation mean (Statue, Fountain, Spot) | PSNR: 23.79 -> 24.17 | Improved |
| add residual R to uncertainty beta (ablation) | OCSplats · Fountain (ablation) | PSNR: 19.97 -> 23.05 | Improved |
| add observation completeness pruning (OCP) (ablation) | OCSplats · Ablation mean (Statue, Fountain, Spot) | PSNR: 24.05 -> 24.17 | Improved |
| add observation completeness correction (OCC) (ablation) | OCSplats · Ablation mean (Statue, Fountain, Spot) | PSNR: 23.86 -> 24.17 | Improved |
| replace fixed threshold with dynamic anchor threshold (ablation) | OCSplats · Ablation mean (Statue, Fountain, Spot) | PSNR: 23.78 -> 24.17 | Improved |
| replace fixed threshold with dynamic anchor threshold (ablation) | OCSplats · Spot (ablation) | PSNR: 25.60 -> 26.32 | Improved |
| add OCC (ablation) | OCSplats · Spot (ablation) | PSNR: 25.72 -> 26.32 | Improved |
| add uncertainty beta to residual R (ablation) | OCSplats · Spot (ablation) | PSNR: 25.21 -> 26.32 | Improved |
| add uncertainty beta to residual R (ablation) | OCSplats · Statue (ablation) | PSNR: 23.16 -> 23.13 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Wild-GS — Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections (NeurIPS 2024) · 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
- From Chaos to Clarity: 3DGS in the Dark (NeurIPS 2024 · similarity 0.87)
- Fix False Transparency by Noise Guided Splatting (NeurIPS 2025 · similarity 0.86)
- IndoorGS: Geometric Cues Guided Gaussian Splatting for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.85)
- Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.85)
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction (NeurIPS 2025 · similarity 0.85)
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers (AAAI 2025 · similarity 0.84)
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.
