AI Paper Atlas

Research map / 3D vision / 3D generation

BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing

Jiacheng Chen, Ramin Mehran, Xuhui Jia, Saining Xie, Sanghyun Woo

ECCV 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing

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 dual-stream architecture (ablation)3DIT one-stream baseline · Objectron (ablation)FID: 6.14 -> 3.52Improved
add dual-stream architecture (ablation)3DIT one-stream baseline · Objectron (ablation)Object PSNR: 13.88 -> 15.90Improved
add Depth Pro and SAM2 depth and segmentation to the source stream (ablation)Dual-stream · Objectron (ablation)FID: 3.52 -> 3.74No clear effect
add Blender renders as 3D-grounded control signals in both streams (ablation)Dual-stream · Objectron (ablation)FID: 3.52 -> 2.93Improved
add source masking training (ablation)DS + Blender · Objectron (ablation)FID: 2.93 -> 2.64Improved
add simulated object jittering training (ablation)DS + Blender + source masking · Objectron (ablation)FID: 2.64 -> 3.25Hurt
initialize WOD training with MOVi-E pretrained checkpoint (ablation)BlenderFusion · WODobject rotationImproved
use BlenderFusion instead of Object 3DITStable Diffusion v2.1 compositor · MOVi-E (standard video setup)Object-level PSNR: 14.06 -> 18.90Improved
use BlenderFusion instead of Neural AssetsStable Diffusion v2.1 compositor · WOD (standard video setup)Frame-level FID: 15.39 -> 10.02Improved
use BlenderFusion instead of Neural Assets in human studyBlenderFusion · Human evaluation (overall)win rate: 87.04 vs 6.40Improved
MOVi-E pre-training for object rotation failures on Objectron (ablation)BlenderFusion · Objectronobject rotationNo clear effect
keep NA at 256x256 instead of higher resolutionNeural Assets · Objectron/WODquantitative metricsNo clear effect

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