AI Paper Atlas

Research map / Point clouds / Shape and surface completion

DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation

Shentong Mo, Enze Xie, Ruihang Chu, Lanqing HONG, Matthias Nießner, Zhenguo Li

NeurIPS 2023 · Point clouds › Shape and surface completion · approach: Point cloud diffusion generation · 12 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
Replace the 3D generation baseline with DiT-3DShapeNet Chair generation · ShapeNet Chair1-NNA CD: 53.70 -> 49.11Improved
Replace the 3D generation baseline with DiT-3DShapeNet Airplane generation · ShapeNet Airplane1-NNA CD: 66.44 -> 62.35Improved
Replace the 3D generation baseline with DiT-3DShapeNet Car generation · ShapeNet CarCOV EMD: 56.53 -> 56.38Hurt
Add voxelization and devoxelized prediction (ablation)DiT-3D point-coordinate baseline · ShapeNet Chair1-NNA CD: 99.86 -> 67.46Improved
Add voxelization and devoxelized prediction (ablation)DiT-3D point-coordinate baseline · ShapeNet ChairCOV CD: 7.768 -> 38.97Improved
Add 3D positional embeddings (ablation)DiT-3D with voxel diffusion · ShapeNet Chair1-NNA CD: 67.46 -> 51.99Improved
Add 3D window attention (ablation)DiT-3D with voxel diffusion and 3D positional embeddings · ShapeNet Chairtraining cost (hours): 91.85 -> 41.67Improved
Add ImageNet pre-training (ablation)DiT-3D · ShapeNet Chair1-NNA CD: 51.99 -> 49.07Improved
Use parameter-efficient fine-tuning of ImageNet-pretrained weights (ablation)DiT-3D · ShapeNet Chair1-NNA CD: 49.07 -> 50.87Mixed
Transfer a source-class model using parameter-efficient fine-tuning (ablation)DiT-3D, Airplane to Chair · ShapeNet Chair1-NNA CD: 51.99 -> 52.56Hurt
Transfer a source-class model using parameter-efficient fine-tuning (ablation)DiT-3D, Chair to Airplane · ShapeNet Airplane1-NNA CD: 62.81 -> 63.58Hurt
Reduce patch size from 4 to 2 (ablation)DiT-3D · ShapeNet Chair1-NNA CD: 51.99 -> 51.78Improved

Later papers that compared with this method

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

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