AI Paper Atlas

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

ICML 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add voxel super-resolution model conditioned on coarse voxels (ablation)HIVE-3D · Voxel SR ablationPSNR: 10.59 -> 11.61Improved
add voxel super-resolution model (ablation)HIVE-3D · Geometry ablation (synthetic)F-Score: 60.09 -> 84.34Improved
increase hierarchy depth from 1 to 3 (ablation)HIVE-3D · Scene tree depth ablationPSNR: 10.13 -> 11.89Improved
increase hierarchy depth from 1 to 3 (ablation)HIVE-3D · Scene tree depth ablationLPIPS: 0.38 -> 0.41No clear effect
add scale factor estimation (ablation)HIVE-3D · Geometry ablation (synthetic)F-Score: 35.44 -> 84.34Improved
use RANSAC registration instead of ICP (ablation)HIVE-3D · Geometry ablation (synthetic)F-Score: 23.92 -> 84.34Improved
use RANSAC registration instead of ICP (ablation)HIVE-3D · Registration and scale ablationPSNR: 16.08 -> 17.00Improved
add scale factor estimation (ablation)HIVE-3D · Registration and scale ablationPSNR: 16.17 -> 17.00Improved
use recursive multi-level refinement instead of direct two-layer partition (ablation)HIVE-3D · qualitative, car scenealignmentImproved
build on TRELLIS with hierarchical voxel enhancementHIVE-3D vs TRELLIS · 3D-FRONT scenesCD: 0.0038 -> 0.0035Improved
build on TRELLIS with hierarchical voxel enhancementHIVE-3D vs TRELLIS · 3D-FRONT scenesIoU: 0.8603 -> 0.7449Hurt
build on TRELLIS with hierarchical voxel enhancementHIVE-3D vs TRELLIS · 3D-FRONT scenesruntime: 6.3s -> 36.5sHurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy