Research map / 3D vision / Gaussian splatting
Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation
Shin-Fang Chng, Sameera Ramasinghe, Jamie Sherrah, Simon Lucey
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 |
|---|---|---|---|
| replace BARF's PE-MLP with coarse-to-fine schedule by Gaussian-activated MLP (GARF) | NeRF with joint pose estimation · LLFF flower | PSNR: 23.58 -> 26.40 | Improved |
| replace BARF with GARF | NeRF with joint pose estimation · LLFF leaves | PSNR: 18.15 -> 19.72 | Improved |
| replace BARF with GARF | NeRF with joint pose estimation · LLFF horns | PSNR: 23.03 -> 22.54 | Hurt |
| replace BARF with GARF | NeRF with joint pose estimation · LLFF fortress | PSNR: 28.48 -> 29.09 | Improved |
| replace BARF with GARF | NeRF with joint pose estimation · LLFF fern | rotation error (deg): 0.16 -> 0.47 | Hurt |
| replace BARF with GARF | NeRF with joint pose estimation · LLFF leaves | rotation error (deg): 1.00 -> 0.13 | Improved |
| replace BARF with GARF | NeRF with joint pose estimation · LLFF horns | rotation error (deg): 0.80 -> 0.03 | Improved |
| replace BARF with GARF | NeRF with joint pose estimation · LLFF room | rotation error (deg): 0.27 -> 0.42 | Hurt |
| initialise weights with perturbation alpha from optimal toward random for SIREN vs GARF (ablation) | SIREN · 2D planar image alignment | reconstruction robustness: SIREN fails drastically starting from alpha=0.3 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- BARF — BARF: Bundle-Adjusting Neural Radiance Fields (ICCV 2021) · better on 12 of 16 shared results
- ref-NeRF — Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (CVPR 2022) · better on 8 of 8 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
- SPARF: Neural Radiance Fields From Sparse and Noisy Poses (CVPR 2023 · similarity 0.90)
- Pose-Free Neural Radiance Fields via Implicit Pose Regularization (ICCV 2023 · similarity 0.90)
- Shape, Pose, and Appearance From a Single Image via Bootstrapped Radiance Field Inversion (CVPR 2023 · similarity 0.89)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.88)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.88)
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.
