Research map / 3D vision / NeRF and radiance fields
LaRa: Efficient Large-Baseline Radiance Fields
Anpei Chen, Haofei Xu, Stefano Esposito, Siyu Tang, Andreas Geiger
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 |
|---|---|---|---|
| increase number of attention groups from 4 to 8 (ablation) | LaRa-fast · Gobjaverse | PSNR: 22.27 -> 23.80 | Improved |
| increase number of attention groups from 8 to 16 (ablation) | LaRa-fast · Gobjaverse | PSNR: 23.80 -> 25.30 | Improved |
| add distortion and normal regularization (ablation) | LaRa-fast · Gobjaverse | PSNR: 26.16 -> 25.30 PSNR; GSO geometry Acc 71.2 -> 70.7 | Mixed |
| use 2D Gaussian splatting instead of 3D Gaussian splatting (ablation) | LaRa-fast · Gobjaverse | PSNR: 26.04 -> 25.30 | No clear effect |
| add fine decoding module on top of coarse decoding (ablation) | LaRa-fast · Gobjaverse | PSNR: 25.06 -> 25.30 | Improved |
| add fine decoding module on top of coarse decoding (ablation) | LaRa-fast · GSO | LPIPS: 0.1017 -> 0.0683 | Improved |
| use spherical harmonics beyond order 0 (ablation) | LaRa-fast · GSO | LPIPS: 0.0743 -> 0.0683 | Improved |
| use Gaussian volume with group attention instead of LGM | LaRa · Co3D | PSNR: 13.81 -> 21.64 | Improved |
| use LaRa vs LGM on GSO LPIPS | LaRa · GSO | LPIPS: 0.0637 -> 0.0616 | No clear effect |
| train 50 epochs instead of 30 epochs (ablation) | LaRa · Gobjaverse | PSNR: 25.30 -> 26.14 | Improved |
Later papers that compared with this method
3 later accepted papers report LaRa as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction (ECCV 2026 · better on 5 of 6 shared results)
- CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling (CVPR 2026 · better on 2 of 2 shared results)
- Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction (CVPR 2025 · better on 2 of 2 shared results)
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.
- MuRF — MuRF: Multi-Baseline Radiance Fields (CVPR 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
- pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024 · similarity 0.89)
- MuRF: Multi-Baseline Radiance Fields (CVPR 2024 · similarity 0.89)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.88)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.88)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.88)
- Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency (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.
