Research map / Image generation / Autoregressive and latent generation
Positional Encoding Field
Yunpeng Bai, Haoxiang Li, Qixing Huang
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 depth-aware 3D RoPE (ablation) | PE-Field · Tanks-and-Temples | PSNR: 21.97 -> 22.12 (full vs w/o multi-level); 20.63 -> 22.12 (w/o depth vs full) | Improved |
| add depth-aware RoPE (ablation) | PE-Field · DL3DV | PSNR: 20.46 -> 22.23 | Improved |
| add multi-level hierarchical RoPE (ablation) | PE-Field · Tanks-and-Temples | PSNR: 21.97 -> 22.12 | Improved |
| add multi-level hierarchical RoPE (ablation) | PE-Field · RE10K | LPIPS: 0.168 -> 0.162 | Improved |
| add both depth and multi-level PE over original PE (ablation) | PE-Field · RE10K | PSNR: 20.17 -> 21.65 | Improved |
| PE-Field versus best baseline GEN3C | Flux.1 Kontext · DL3DV | PSNR: 19.14 -> 22.23 | Improved |
| multi-step progressive view transformation (5 steps) vs one step (ablation) | PE-Field · large viewpoint changes | consistency (qualitative) | Improved |
Closest papers by meaning
- DiT4Edit: Diffusion Transformer for Image Editing (AAAI 2025 · similarity 0.88)
- Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis (ICLR 2024 · similarity 0.87)
- Cameras as Relative Positional Encoding (NeurIPS 2025 · similarity 0.87)
- DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking (NeurIPS 2026 · similarity 0.87)
- VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control (ICLR 2025 · similarity 0.86)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · similarity 0.86)
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.
