Research map / 3D vision / 3D generation
HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
Bin Zang, Wenting Zheng, Xiaoliang Luo, Zhiyuan Fang, Shi Li, Lvchun Wang, Wei Yu, Yi Zhao, Tian Xie, Yuchi Huo, Rengan Xie
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 voxel super-resolution model conditioned on coarse voxels (ablation) | HIVE-3D · Voxel SR ablation | PSNR: 10.59 -> 11.61 | Improved |
| add voxel super-resolution model (ablation) | HIVE-3D · Geometry ablation (synthetic) | F-Score: 60.09 -> 84.34 | Improved |
| increase hierarchy depth from 1 to 3 (ablation) | HIVE-3D · Scene tree depth ablation | PSNR: 10.13 -> 11.89 | Improved |
| increase hierarchy depth from 1 to 3 (ablation) | HIVE-3D · Scene tree depth ablation | LPIPS: 0.38 -> 0.41 | No clear effect |
| add scale factor estimation (ablation) | HIVE-3D · Geometry ablation (synthetic) | F-Score: 35.44 -> 84.34 | Improved |
| use RANSAC registration instead of ICP (ablation) | HIVE-3D · Geometry ablation (synthetic) | F-Score: 23.92 -> 84.34 | Improved |
| use RANSAC registration instead of ICP (ablation) | HIVE-3D · Registration and scale ablation | PSNR: 16.08 -> 17.00 | Improved |
| add scale factor estimation (ablation) | HIVE-3D · Registration and scale ablation | PSNR: 16.17 -> 17.00 | Improved |
| use recursive multi-level refinement instead of direct two-layer partition (ablation) | HIVE-3D · qualitative, car scene | alignment | Improved |
| build on TRELLIS with hierarchical voxel enhancement | HIVE-3D vs TRELLIS · 3D-FRONT scenes | CD: 0.0038 -> 0.0035 | Improved |
| build on TRELLIS with hierarchical voxel enhancement | HIVE-3D vs TRELLIS · 3D-FRONT scenes | IoU: 0.8603 -> 0.7449 | Hurt |
| build on TRELLIS with hierarchical voxel enhancement | HIVE-3D vs TRELLIS · 3D-FRONT scenes | runtime: 6.3s -> 36.5s | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MIDI — MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation (CVPR 2025) · better on 3 of 3 shared results
- SceneGen — SceneGen: Learning To Generate Realistic Traffic Scenes (CVPR 2021) · better on 3 of 3 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
- XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies (CVPR 2024 · similarity 0.86)
- DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior (ICLR 2024 · similarity 0.86)
- LT3SD: Latent Trees for 3D Scene Diffusion (CVPR 2025 · similarity 0.86)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.85)
- SCube: Instant Large-Scale Scene Reconstruction using VoxSplats (NeurIPS 2024 · similarity 0.85)
- Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity (NeurIPS 2025 · similarity 0.85)
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.
