AI Paper Atlas

Research map / 3D vision / 3D generation

HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields

Zuhao Liu, Melih Darcan, Zhengdi Yu, Riza Alp Guler, Tolga Birdal

NeurIPS 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 0 citations (OpenAlex)

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 HaNDF, object-conditioned neural distance fields serving as data-driven priors over plausible hand-object configurations in the product manifold of hand articulations.

Problem

Unconditional generative priors model human pose well, but hands interact with objects, so a generative prior conditioned on objects is needed to model plausible hand-object configurations.

Approach

Object-conditional neural distance fields defined over the product manifold of hand articulations, used as data-driven priors for hand-object configurations, extending unconditional pose priors to object-conditioned ones.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Riemannian distance field instead of Euclidean (ablation)HaNDF (MLP + object condition) · HOI4D denoising sigma=0.8delta_q (degrees): 8.15 -> 5.98Improved
use Riemannian field instead of Euclidean with transformer and object condition (ablation)HaNDF (Transformer) · HOI4D denoising sigma=0.8delta_q (degrees): 10.27 -> 5.52Improved
add object condition (object token) (ablation)HaNDF (Transformer, Riemannian) · HOI4D denoising sigma=0.8delta_q (degrees): 6.10 -> 5.52Improved
condition on the correct object instead of a random wrong-category object (ablation)HaNDF · HOI4D denoising sigma=0.8delta_q (degrees): 5.80 -> 5.52Improved
use transformer instead of MLP backbone with object condition and Riemannian field (ablation)HaNDF · HOI4D denoising sigma=0.8delta_q (degrees): 5.98 -> 5.52Improved
use DeepSDF-style auto-decoder object code instead of COD-VAE or Tencent-XR-3DGen (ablation)HaNDF · HOI4D denoising sigma=0.8delta_q (degrees): 6.11 -> 5.52 (COD-VAE); 5.70 -> 5.52 (3DGen)Improved
encode object code as 1 token instead of 64 tokens (ablation)HaNDF · HOI4D denoising sigma=0.8delta_q (degrees): 6.40 -> 5.52Improved
increase transformer depth from 4 to 8 layers (ablation)HaNDF · HOI4D denoising sigma=0.8dNN (degrees): 4.96 -> 5.07Hurt
increase transformer depth from 2 to 4 layers (ablation)HaNDF · HOI4D denoising sigma=0.8delta_q and dNN (degrees): delta_q 4.95 -> 5.52; dNN 6.08 -> 4.96Mixed
plug HaNDF into AlignSDF as hand refinement priorAlignSDF · HOI4D hand-object recoverydelta_q (degrees): 14.77 -> 9.60Improved
add nearest-neighbor object retrieval in DeepSDF latent spaceAlignSDF + HaNDF · HOI4D hand-object recoveryobj-F@2%: 0.1187 -> 0.1568Improved
use K=8 object optimization instead of K=1 retrievalAlignSDF + HaNDF · HOI4D hand-object recoveryobj-CD: obj-CD 0.0896 -> 0.1083; MPJPE 11.50 -> 11.45Mixed

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