Research map / 3D vision / 3D generation
WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image
Jiwoo Park, Tae Eun Choi, Youngjun Jun, Seong Jae Hwang
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 pose-aware noise initialization (PANI) (ablation) | WAVE on MegaScenes · MegaScenes | LPIPS-next: 0.607 -> 0.560 | Improved |
| add warp-guided adaptive attention (WGAA) (ablation) | WAVE on MegaScenes · MegaScenes | LPIPS-next: 0.607 -> 0.416 | Improved |
| combine PANI with WGAA (ablation) | WAVE on MegaScenes · MegaScenes | LPIPS-next: 0.416 -> 0.397 | Improved |
| use warp-masked adaptive attention instead of conventional batch self-attention (ablation) | MegaScenes + WAVE · DTU | Angular Consistency: 16.09 -> 6.32 | Improved |
| apply WAVE to MegaScenes | MegaScenes · DTU | LPIPS-next: 0.379 -> 0.130 | Improved |
| apply WAVE to ZeroNVS | ZeroNVS · RE10K sequence | FID: 24.13 -> 25.67 | Hurt |
| apply WAVE to MegaScenes | MegaScenes · RE10K orbit | LPIPS-first: 0.722 -> 0.728 | No clear effect |
| apply WAVE to MegaScenes | MegaScenes · RE10K sequence | PSNR: 12.02 -> 13.27 | Improved |
| use WAVE-generated views for 3D Gaussian splatting | MegaScenes · DTU 3DGS downstream | PSNR: 20.43 -> 26.95 | Improved |
| use WAVE-generated views for 3D Gaussian splatting | MegaScenes · Mip-NeRF 360 3DGS downstream | LPIPS: PSNR 25.07 -> 26.30; LPIPS 0.074 -> 0.082 | Mixed |
| use smaller Depth Anything model (DA-S) for warping (ablation) | WAVE · MegaScenes | LPIPS-next: 0.397 -> 0.415 | No clear effect |
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.
- ZeroNVS — ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image (CVPR 2024) · better on 2 of 2 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
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.90)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.89)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.89)
- ViewFusion: Towards Multi-View Consistency via Interpolated Denoising (CVPR 2024 · similarity 0.88)
- HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D (CVPR 2024 · similarity 0.88)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 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.
