AI Paper Atlas

Research map / Point clouds / Shape and surface completion

HilbertGen-3D:Hilbert--Multifractal Conditioning for Topology-Aware 3D Generation

Ziyi Zhang, Shixuan Li, Yorie Nakahira, Paul Bogdan, Guannan Qu

NeurIPS 2026 · Point clouds › Shape and surface completion · approach: Point cloud diffusion generation

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes HilbertGen-3D, a diffusion-based 3D point cloud generator conditioned on Hilbert-curve and multifractal descriptors to capture global topological structure.

Problem

Diffusion-based point cloud generation relies on local voxel or patch features and often misses global structural organization, which matters for game assets, medical imaging, and VR/AR.

Approach

Conditions a diffusion model for 3D point cloud generation on Hilbert-curve ordering and multifractal (topology-aware) conditioning signals to encode global structure; details beyond the abstract are unknown.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add HMC conditioning (VAE variant) on top of the DiT-3D bottleneck backboneTopoDiT-3D · ShapeNet Car, 1-NNA-EMD1-NNA-EMD (distance from 50): 59.09 -> 49.81Improved
add HMC conditioning (VAE variant)TopoDiT-3D · ShapeNet Chair, COV-CDCOV-CD: 56.67 -> 54.32Hurt
add HMC conditioning (bank variant)TopoDiT-3D · ShapeNet Car, COV-EMDCOV-EMD: 51.98 -> 57.86Improved
add HMC conditioning (bank variant)TopoDiT-3D · ShapeNet Chair, 1-NNA-CD1-NNA-CD: 48.87 -> 49.01No clear effect
add HMC conditioning (both variants)TopoDiT-3D · ShapeNet Airplane1-NNA and COV: bank 1-NNA-CD 57.15 -> 54.79Improved
add HMC conditioning (both variants)TopoDiT-3D · ShapeNet Lamp and Vessel1-NNA and COV: Vessel 1-NNA-EMD 78.96 -> 49.05 (bank)Improved
remove HMC tokens (ablation)HilbertGen-3D · ShapeNet Airplane ablation1-NNA-CD: 57.33 -> 55.57 when HMC tokens addedImproved
add global HMC embedding (ablation)HilbertGen-3D · ShapeNet Airplane ablationCOV-CD: COV-CD 60.24 -> 60.98; 1-NNA-EMD 53.58 -> 53.66Mixed
add bottleneck fusion (ablation)HilbertGen-3D · ShapeNet Airplane ablation1-NNA-CD: 60.00 -> 55.57Improved
add bottleneck fusion (ablation)HilbertGen-3D · ShapeNet Airplane ablationCOV-CD: 55.92 -> 60.98Improved
use VAE-generated versus bank-sampled HMC conditions (ablation)HilbertGen-3D · ShapeNet Chair, Airplane, Car1-NNA and COVMixed

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