AI Paper Atlas

Research map / 3D vision / 3D generation

DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation

Ziang Cao, Fangzhou Hong, Tong Wu, Liang Pan, Ziwei Liu

TPAMI 2025 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 9 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 triplane regularization (TV and L2) (ablation)diffusion on fitted triplanes · OmniObject3DFID: 125.21 -> 113.01Improved
add triplane normalization (ablation)diffusion on fitted triplanes · OmniObject3DFID: 113.01 -> 109.81Improved
add cross-plane attention 3D-aware encoder/decoder (ablation)DiffTF · OmniObject3DFID: 109.81 -> 39.13Improved
replace CP-TF with original 2D transformer (ablation)CP encoder model · OmniObject3DFID: 39.13 -> 52.35Hurt
add 3D-aware transformer (CP-TF) (ablation)CP encoder model · OmniObject3DFID: 39.13 -> 25.36Improved
replace 3D-aware convolution with the proposed 3D-aware modules (ablation)DiffTF · OmniObject3DFID: 84.55 -> 25.36Improved
add multi-view reconstruction loss (ablation)DiffTF · OmniObject3DFID: 25.36 -> 23.30Improved
add 3D-aware refinement (ablation)DiffTF + reconstruction loss · OmniObject3DFID: 23.30 -> 20.97Improved
DiffTF to DiffTF++ (loss + refinement)DiffTF · OmniObject3DFID: 25.36 -> 20.97Improved
DiffTF to DiffTF++DiffTF · ShapeNet CarFID: 36.68 -> 32.74Improved
DiffTF to DiffTF++DiffTF · ShapeNet PlaneFID: 14.46 -> 11.32Improved
DiffTF to DiffTF++DiffTF · ShapeNet ChairFID: 35.16 -> 31.52Improved

Later papers that compared with this method

1 later accepted paper reports DiffTF as a baseline in their results tables; 1 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 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