Research map / 3D vision / 3D generation
AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction
Xuying Zhang, Yupeng Zhou, Kai Wang, Yikai Wang, Zhen Li, Shaohui Jiao, Daquan Zhou, Qibin Hou, Ming-Ming Cheng
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 Stacked-LE local conditioning (ablation) | Zero123++ baseline · Objaverse held-out (300 objects) | PSNR, LPIPS, SSIM, CLIP-score | Improved |
| add LSTM-GE global conditioning (ablation) | Zero123++ baseline · Objaverse held-out (300 objects) | PSNR, LPIPS, SSIM, CLIP-score | Improved |
| combine Stacked-LE and LSTM-GE with next-view autoregression (ablation) | Zero123++ baseline · Objaverse held-out (300 objects) | PSNR, LPIPS, SSIM, CLIP-score | Improved |
| generate views in normal near-to-far order instead of random order (ablation) | AR-1-to-3 · Objaverse held-out (300 objects) | PSNR, LPIPS, SSIM, CLIP-score | Improved |
| generate views in normal order instead of reverse far-to-near order (ablation) | AR-1-to-3 · Objaverse held-out (300 objects) | PSNR, LPIPS, SSIM, CLIP-score | No clear effect |
| encode global view features with LSTM instead of matmul variant (ablation) | AR-1-to-3 · Objaverse held-out (300 objects) | PSNR, LPIPS, SSIM, CLIP-score | Improved |
Closest papers by meaning
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.89)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.89)
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis (NeurIPS 2026 · similarity 0.89)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.89)
- MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model (CVPR 2025 · similarity 0.89)
- DreamComposer: Controllable 3D Object Generation via Multi-View Conditions (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.
