AI Paper Atlas

Research map / 3D vision / 3D generation

TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation

Nikolai Kalischek, Torben Peters, Jan Dirk Wegner, Konrad Schindler

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 6 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
prune unoccupied tetrahedra from the grid (ablation)TetraDiffusion R=128 · Training memoryGPU memory (GB): 20.8 -> 12.0Improved
prune unoccupied tetrahedra from the grid (ablation)TetraDiffusion R=192 · Training memoryGPU memory (GB): 78.2 -> 20.9Improved
convolve natively on tetrahedral grid instead of embedding in a voxel grid (MeshDiffusion)TetraDiffusion · Training memory at R=128GPU memory (GB): 76.6 -> 20.8Improved
native tetrahedral convolution instead of MeshDiffusion voxel embeddingTetraDiffusion · Inferences/obj: 714.3 -> 3.4Improved
randomize neighbor ordering in tetrahedral convolution (ablation)TetraDiffusion · ShapeNet motorbikeconvergence / sample qualityHurt
replace TetraConv with permutation-invariant graph convolutions, even with matched parameter count (ablation)TetraDiffusion · ShapeNet motorbikeconvergence / sample qualityHurt
increase native resolution to R=192 versus R=128 baselines (ablation)TetraDiffusion · Shape qualityshading-FIDImproved
reduce sampling to 32 diffusion steps (ablation)TetraDiffusion · Supplement step-count studymesh qualityNo clear effect
TetraDiffusion versus NWD on chairsTetraDiffusion · ShapeNet Chairshading-FID: 16.7 -> 39.9Hurt

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