AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion

Ziya Erkoç, Fangchang Ma, Qi Shan, Matthias Nießner, Angela Dai

ICCV 2023 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 101 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
initialize all MLPs from the first optimized MLP instead of random init (ablation)HyperDiffusion · ShapeNet AirplaneFPD: 4.01 -> 3.49Improved
initialize all MLPs from the first optimized MLP instead of random init (ablation)HyperDiffusion · ShapeNet AirplaneMMD: 3.34 -> 3.45Hurt
add positional encoding to the per-sample MLP (ablation)HyperDiffusion · ShapeNet AirplaneFPD: 6.40 -> 3.49Improved
add positional encoding to the per-sample MLP (ablation)HyperDiffusion · ShapeNet Airplane1-NNA (%): 76.5 -> 69.3Improved
diffuse MLP weights instead of voxel gridsunconditional 4D generation · DeformingThings4D1-NNA (%): 85 -> 62Improved
diffuse MLP weights instead of voxel gridsunconditional 3D generation · ShapeNet AirplaneFPD: 38.9 -> 3.5Improved
weight-space diffusion versus point-cloud diffusion baselines (PVD, DPC)unconditional 3D generation · ShapeNet ChairFPD: 3.5 -> 1.7Improved
weight-space diffusion versus point-cloud diffusion baselines on MMDunconditional 3D generation · ShapeNet ChairMMD: 6.3 -> 7.1Hurt
add a naive secondary surface reconstruction loss to the diffusionHyperDiffusion · 3D shape generationgeneration qualityNo clear effect

Later papers that compared with this method

3 later accepted papers report HyperDiffusion as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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