AI Paper Atlas

Research map / 3D vision / 3D generation

Texture Generation Using Dual-Domain Feature Flow with Multi-View Hallucinations

Seunggyu Chang, Jungchan Cho, Songhwai Oh

AAAI 2022 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 2 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
Use the full dual-domain method rather than the strongest listed baselinePose transfer and texture-rendering system · DeepFashionFID: 10.573 -> 9.001Improved
Use the full dual-domain method rather than the strongest listed baselinePose transfer and texture-rendering system · DeepFashionLPIPS: 0.234 -> 0.156Improved
Use the full dual-domain method rather than the strongest listed baselinePose transfer and texture-rendering system · DeepFashionSSIM: 0.763 -> 0.830Improved
Use the full dual-domain method rather than the strongest listed baselinePose transfer and texture-rendering system · iPERLPIPS: 0.087 -> 0.051Improved
Use the full dual-domain method rather than the strongest listed baselinePose transfer and texture-rendering system · iPERSSIM: 0.854 -> 0.907Improved
Add image-to-texture attention to the independent model (ablation)Texture generator G_T · iPERLPIPS: 0.075 -> 0.073Improved
Add image-to-texture attention to the independent model (ablation)Texture generator G_T · FashionVidLPIPS: 0.100 -> 0.083Improved
Add texture-to-image attention to the image-to-texture-only model (ablation)Texture generator G_T · iPERLPIPS: 0.073 -> 0.063Improved
Add texture-to-image attention to the image-to-texture-only model (ablation)Texture generator G_T · FashionVidSSIM: 0.902 -> 0.903Improved
Add both inter-domain attention paths (ablation)Image generator G_I · FashionVidSSIM: 0.913 -> 0.921Improved
Add either single inter-domain attention path (ablation)Image generator G_I · iPERLPIPS: 0.051 -> 0.056; 0.051 -> 0.061Mixed
Increase hallucination views from one to two (ablation)G_I and G_T · iPERSSIM: 0.894 -> 0.907; 0.887 -> 0.898Improved

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