Research map / 3D vision / Gaussian splatting
WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild
Yuhao Bai, Qianqiu Tan, Lilong Chen, Huanhuan Lv, Lijun Chen
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 beta-VAE latent appearance space instead of discrete per-image embeddings (ablation) | WilLaGS · Photo Tourism (avg) | PSNR (dB): 21.15 -> 25.51 | Improved |
| add beta-VAE latent appearance space instead of discrete per-image embeddings (ablation) | WilLaGS · NeRF-OSR (avg) | PSNR (dB): 22.97 -> 25.79 | Improved |
| add latent-conditioned Tri-Plane appearance field (ablation) | WilLaGS · Photo Tourism (avg) | PSNR (dB): 23.97 -> 25.51 | Improved |
| add latent-conditioned Tri-Plane appearance field (ablation) | WilLaGS · NeRF-OSR (avg) | PSNR (dB): 24.55 -> 25.79 | Improved |
| add teacher-student perceptual masking (ablation) | WilLaGS · Photo Tourism (avg) | PSNR (dB): 25.53 -> 25.51 | No clear effect |
| add teacher-student perceptual masking (ablation) | WilLaGS · Photo Tourism (avg) | LPIPS: 0.162 -> 0.151 | Improved |
| add teacher-student perceptual masking (ablation) | WilLaGS · NeRF-OSR (avg) | PSNR (dB): 25.63 -> 25.79 | Improved |
| use WilLaGS instead of AsymGS | AsymGS · Photo Tourism Trevi Fountain | PSNR (dB): 23.61 -> 24.27 | Improved |
| use WilLaGS instead of WildGaussians | WildGaussians · Training cost | GPU hours: 7.8 -> 0.9 | Improved |
| use WilLaGS instead of GS-W | GS-W · NeRF-OSR stjohann | PSNR (dB): 27.19 -> 26.13 | Hurt |
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.
- WildGaussians — WildGaussians: 3D Gaussian Splatting In the Wild (NeurIPS 2024) · better on 6 of 6 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
- Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting (AAAI 2025 · similarity 0.91)
- Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.91)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.90)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.90)
- Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis (NeurIPS 2024 · similarity 0.90)
- HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
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.
