Research map / 3D vision / Gaussian splatting
Continuous Viewpoint Adaptation for Single View 3D Object Reconstruction
Seunghyun Hwang, Qiang Qiu
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 world-space camera pose input (ablation) | Splatter Image · ShapeNet-Cars (short training) | PSNR: 21.81 -> 22.13 | Improved |
| add filter-atom decomposition with MLP atom generator (DCF) (ablation) | Splatter Image + camera · ShapeNet-Cars (short training) | PSNR: 22.13 -> 22.19 | Improved |
| replace MLP atom generator with NODE conditioned on azimuth (ablation) | Splatter Image + DCF · ShapeNet-Cars (short training) | PSNR: 22.19 -> 22.64 | Improved |
| also condition NODE initial state on polar angle (ablation) | Splatter Image + ODE(Phi) · ShapeNet-Cars (short training) | PSNR: 22.64 -> 23.12 | Improved |
| full view-adaptive NODE model vs vanilla (ablation) | Splatter Image · ShapeNet-Cars (short training) | LPIPS: 0.166 -> 0.129 | Improved |
| continuous view-adaptive filter atoms vs Splatter Image | Splatter Image · ShapeNet-Chairs view interpolation | PSNR: 21.59 -> 23.51 | Improved |
| continuous view-adaptive filter atoms vs Splatter Image | Splatter Image · ShapeNet-Chairs view extrapolation | PSNR: 20.82 -> 21.48 | Improved |
| continuous view-adaptive filter atoms vs Splatter Image | Splatter Image · ShapeNet-Cars view extrapolation | PSNR: 22.14 -> 22.59 | Improved |
| continuous view-adaptive filter atoms vs Splatter Image | Splatter Image · Google Scanned Objects | PSNR: 21.06 -> 21.74 | Improved |
| continuous view-adaptive filter atoms vs Splatter Image (trained on Cars, tested on Chairs) | Splatter Image · Unseen category ShapeNet-Cars train | PSNR: 14.49 -> 15.24 | Improved |
| continuous view-adaptive filter atoms vs Splatter Image (trained on Chairs) | Splatter Image · Unseen category ShapeNet-Chairs train | PSNR: 16.45 -> 16.46 | No clear effect |
| continuous view-adaptive filter atoms vs Splatter Image | Splatter Image · NMR multi-category ShapeNet | PSNR: 29.38 -> 29.51 | Improved |
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.
- Splatter Image — Splatter Image: Ultra-Fast Single-View 3D Reconstruction (CVPR 2024) · better on 12 of 15 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
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.89)
- Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views (CVPR 2025 · similarity 0.89)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.89)
- SfM-Free 3D Gaussian Splatting via Hierarchical Training (CVPR 2025 · similarity 0.89)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
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.
