AI Paper Atlas

Research map / 3D vision / 3D generation

AutoPhyX: Automatic Text-Condition Physics Property Generation

Bei Huang, Yixin Chen, Hongbin Zha, Yuru Pei, Siyuan Huang

ECCV 2026 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 0 citations (OpenAlex)

Read the paper

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
AutoPhyX with OpenCLIP instead of Pixie with CLIP featuresPixie · Text2PhyX testPSNR: 23.421 -> 26.012Improved
use OpenCLIP features instead of CLIP (ablation)AutoPhyX · Text2PhyX testPSNR: 25.105 -> 26.012Improved
use OpenCLIP features instead of CLIP (ablation)AutoPhyX · Text2PhyX testAvg. physical error: 0.069 -> 0.059Improved
add text conditioning via FiLM (ablation)AutoPhyX · Human-annotated test (30 objects)log E error: 0.624 -> 0.181Improved
add text conditioning via FiLM (ablation)AutoPhyX · Human-annotated test (30 objects)log rho error: 0.287 -> 0.102Improved
use FiLM U-Net instead of 3D Transformer (16^3) (ablation)AutoPhyX · Text2PhyX subsetlog E error: 0.142 -> 0.054Improved
use FiLM U-Net instead of VisualRWKV (32^3) (ablation)AutoPhyX · Text2PhyX subsetlog E error: 0.106 -> 0.054Improved
use FiLM U-Net instead of MLP with concatenated input (ablation)AutoPhyX · Text2PhyX subsetlog E error: 0.316 -> 0.054Improved
raise VisualRWKV input resolution from 16^3 to 32^3 (ablation)VisualRWKV · Text2PhyX subsetlog E error: 0.149 -> 0.106Improved
AutoPhyX versus Gemini VLM direct predictionGemini · Text2PhyX testAvg. physical error: 0.218 -> 0.059Improved
unconditional AutoPhyX versus Pixie on Pixie datasetPixie · Pixie dataset (unconditional)log E error: 0.022 -> 0.063Hurt
unconditional AutoPhyX versus PixiePixie · Text2PhyX (unconditional)log E error: 0.059 -> 0.042Improved

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