Research map / 3D vision / Gaussian splatting
GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidance
Weiqi Zhang, Junsheng Zhou, Haotian Geng, Kanle Shi, Shenkun Xu, Yi Fang, Yu-Shen Liu
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 overlap detection with camera pose optimization (extra views) (ablation) | GaussianGrow · Objaverse texturing | FID: 40.48 -> 36.07 | Improved |
| add overlap detection with camera pose optimization (extra views) (ablation) | GaussianGrow · Objaverse texturing | KID x10^-3: 4.81 -> 3.04 | Improved |
| add image-level inpainting for hard-to-observe regions (ablation) | GaussianGrow · Objaverse texturing | FID: 40.46 -> 36.07 | Improved |
| add image-level inpainting for hard-to-observe regions (ablation) | GaussianGrow · Objaverse texturing | CLIP score: 26.71 -> 27.30 | Improved |
| use 10 views instead of 6 cardinal views (ablation) | GaussianGrow · Objaverse texturing | FID: 40.48 -> 36.07 | Improved |
| increase views from 10 to 12 (ablation) | GaussianGrow · Objaverse texturing | FID: 36.07 -> 36.57 | No clear effect |
| increase views from 10 to 12 (ablation) | GaussianGrow · Objaverse texturing | CLIP score: 27.30 -> 26.48 | Hurt |
| use retrieved point clouds (Uni3D) instead of LGM-generated scaffold | GaussianGrow · T3Bench | CLIP similarity (%): 30.17 -> 31.55 | Improved |
| replace LGM appearance with GaussianGrow appearance on LGM geometry | LGM · T3Bench | CLIP similarity (%): 29.96 -> 30.17 | Improved |
| run baselines on reconstructed mesh (BPA) instead of GT-like input | SyncMVD · Objaverse texturing | FID: 40.85 -> 60.29 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DiffSplat — DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation (ICLR 2025) · better on 3 of 3 shared results
- Paint3D — Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024) · better on 3 of 3 shared results
- Text2Tex — Text2Tex: Text-driven Texture Synthesis via Diffusion Models (ICCV 2023) · better on 3 of 3 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
- GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance (AAAI 2025 · similarity 0.90)
- Lightweight Predictive 3D Gaussian Splats (ICLR 2025 · similarity 0.88)
- Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians (CVPR 2025 · similarity 0.88)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- Text-to-3D using Gaussian Splatting (CVPR 2024 · similarity 0.87)
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.
