Research map / 3D vision / 3D generation
DreamCube: RGB-D Panorama Generation via Multi-plane Synchronization
Yukun Huang, Yanning Zhou, Jianan Wang, Kaiyi Huang, Xihui Liu
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 multi-plane synchronization (all synced operators) (ablation) | DreamCube · Structured3D ablation | FID: 21.35 -> 12.58 | Improved |
| add multi-plane synchronization (all synced operators) (ablation) | DreamCube · Structured3D ablation | delta-1.25: 0.684 -> 0.787 | Improved |
| add XYZ positional encoding instead of none (ablation) | DreamCube · Structured3D ablation | FID: 13.66 -> 12.58 | Improved |
| add synced self-attention (ablation) | DreamCube · Structured3D ablation | FID: 24.38 -> 12.58 | Improved |
| add synced convolution (ablation) | DreamCube · Structured3D ablation | FID: 19.62 -> 12.58 | Improved |
| add synced group normalization (ablation) | DreamCube · Structured3D ablation | FID: 18.35 -> 12.58 | Improved |
| add synced self-attention to the U-Net (ablation) | DreamCube · Efficiency (U-Net forward pass) | latency: 139.4 -> 297.1 ms | Hurt |
| use cubemap RGB-D generation instead of equirectangular RGB-D (vs PanoDiffusion) | DreamCube · Structured3D RGB panorama | FID: 16.20 -> 12.58 | Improved |
| use joint RGB-D cubemap generation instead of depth estimation (vs DAC) | DreamCube · Structured3D depth panorama | delta-1.25: 0.751 -> 0.787 | Improved |
Closest papers by meaning
- DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion (NeurIPS 2024 · similarity 0.88)
- CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation (ICLR 2025 · similarity 0.87)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 2025 · similarity 0.87)
- HORIZON: High-Resolution Semantically Controlled Panorama Synthesis (AAAI 2024 · similarity 0.86)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.86)
- 4K4DGen: Panoramic 4D Generation at 4K Resolution (ICLR 2025 · 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.
