Research map / 3D vision / 3D generation
Landscape-Awareness for Geometric View Diffusion Model
Yan-Ting Chen, Hao-Wei Chen, Tsu-Ching Hsiao, Chun-Yi Lee
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 score-based Stage 1 before Zero123 refinement (multi-view, 2 images) (ablation) | Two-stage pose estimation · Multi-view pose estimation | R@15: 0.200 -> 0.540 | Improved |
| add score-based Stage 1 (8 images) (ablation) | Two-stage pose estimation · Multi-view pose estimation | R@30: 0.050 -> 0.786 | Improved |
| add Zero123 Stage 2 refinement (8 images) (ablation) | Two-stage pose estimation · Multi-view pose estimation | R@15: 0.289 -> 0.643 | Improved |
| add Zero123 Stage 2 refinement (2 images) (ablation) | Two-stage pose estimation · Multi-view pose estimation | R@30: 0.450 -> 0.580 | Improved |
| use direct score prediction instead of energy-based modeling (ablation) | Stage 1 guidance model · GSO (10 objects) | SR@15: 0.726 -> 0.900 | Improved |
| use direct score prediction instead of energy-based modeling (ablation) | Stage 1 guidance model · GSO (10 objects) | R@15: 0.850 -> 0.963 | Improved |
| use direct score prediction instead of energy-based modeling (ablation) | Stage 1 guidance model · GSO (10 objects) | Translation error: 0.044 -> 0.051 | Hurt |
| add score-guided Stage 1 to iFusion's Zero123 MSE optimization | iFusion · GSO (synthetic) | SR@15: 0.365 -> 0.811 | Improved |
| add score-guided Stage 1 to iFusion's Zero123 MSE optimization | iFusion · OO3D (synthetic) | SR@15: 0.306 -> 0.780 | Improved |
| add score-guided Stage 1 to iFusion on real data | iFusion · HOPEv2 (real) | SR@30: 0.206 -> 0.786 | Improved |
| add score-guided Stage 1 to iFusion | iFusion · GSO (synthetic) | R@5: 0.700 -> 0.645 | Hurt |
| add score-guided Stage 1 to iFusion on unseen objects | iFusion · GSO unseen objects (10) | R@5: 0.625 -> 0.489 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- VGGT — VGGT: Visual Geometry Grounded Transformer (CVPR 2025) · better on 2 of 4 shared results
- DUSt3R — DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024) · better on 4 of 4 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
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.89)
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis (NeurIPS 2026 · similarity 0.88)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.87)
- Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis (NeurIPS 2026 · similarity 0.87)
- DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion (CVPR 2025 · similarity 0.87)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · 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.
