AI Paper Atlas

Research map / Point clouds / Shape and surface completion

HVPUNet: Hybrid-Voxel Point-cloud Upsampling Network

Juhyung Ha, Vibhas Kumar Vats, Soon-heung Jung, Alimoor Reza, David J. Crandall

ICCV 2025 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 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 operational voxel expansion (ablation)HVPUNet · PU-GANDice/IoUImproved
add distance-based pruning (ablation)HVPUNet · PU-GANDice/IoUImproved
raise expansion kernel threshold to 5 or above, optimal 7 (ablation)HVPUNet · PU-GANDice/IoU: 5 -> 7Improved
HVPUNet instead of RepKPU, inference speedHVPUNet · PU-GANruntime (sec): 345.387 -> 1.543Improved
HVPUNet instead of RepKPU, memoryHVPUNet · PU-GANVRAM (GB): 33.621 -> 2.817Improved
HVPUNet instead of Grad-PU, DiceHVPUNet · PU-GANDice: 0.698 -> 0.707Improved
HVPUNet instead of Grad-PU, P2F averageHVPUNet · PU-GANP2F avg (x10^3): 2.143 -> 2.736Hurt
HVPUNet instead of RepKPU, P2F maxHVPUNet · PU-GANP2F max (x10^3): 46.822 -> 26.023Improved
HVPUNet under 512-point undersampled input instead of RepKPUHVPUNet · PU-GANDice: 0.550 -> 0.604Improved
HVPUNet instead of RepKPU on PU1K P2F maxHVPUNet · PU1KP2F max (x10^3): 13.872 -> 25.438Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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