AI Paper Atlas

Research map / 3D vision / 3D generation

CyC3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization

Hongbin Xu, Chaohui Yu, Feng Xiao, Jiazheng Xing, Hai Ci, Weitao Chen, Fan Wang, Ming Li

AAAI 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 1 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 2D condition cycle consistency loss L_cond (ablation)CyC3D-D · GSO edgePSNR: 12.87 -> 15.09Improved
Add 2D condition cycle consistency loss L_cond (ablation)CyC3D-D · GSO sketchPSNR: 17.52 -> 18.38Improved
Add 2D cycle consistency loss L_cond (ablation)CyC3D-D · GSO depthR-MSE: 0.0650 -> 0.0321Improved
Add 3D depth/normal condition cycle loss L_cond-d on top of L_cond (ablation)CyC3D-D · GSO depthR-MSE: 0.0321 -> 0.0060Improved
Add view cycle consistency (render + CLIP semantic loss) (ablation)CyC3D · controllable 3D generation (qualitative)3D shape qualityImproved
Train with cycle consistency (CyC3D-D vs ControLRM-D backbone)CyC3D-D · GSO depthR-MSE: 0.0650 -> 0.0060Improved
Train with cycle consistency (CyC3D-D vs ControLRM-D)CyC3D-D · GSO edgePSNR: 12.47 -> 15.09Improved
Train with cycle consistency (CyC3D-D vs ControLRM-D)CyC3D-D · GOBJ to GSO generation qualityFID: 171.13 -> 168.71No clear effect
Train with cycle consistency (CyC3D-T vs ControLRM-T)CyC3D-T · GOBJ to GSO generation qualityFID: 260.75 -> 255.30No clear effect
Use transformer backbone (CyC3D-T) vs diffusion backbone (CyC3D-D)CyC3D · GOBJ to GSO generation qualityFID: 168.71 (D) vs 255.30 (T)Hurt

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