AI Paper Atlas

Research map / 3D vision / 3D generation

Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image

Zidian Qiu, Ancong Wu

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 0 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 pseudo-geometry distillation loss (ablation)Alignment-VGGT · 3D-FRONT test set, alignment loss ablationCD-S: 0.8688 -> 0.1266Improved
add mask regularization loss (ablation)Alignment-VGGT · 3D-FRONT test set, alignment loss ablationCD-S: 0.1266 -> 0.1120Improved
add mask regularization loss (ablation)Alignment-VGGT · 3D-FRONT test set, alignment loss ablationIoU-B: 0.4670 -> 0.4818Improved
add camera intrinsics and extrinsics as input (ablation)Alignment-VGGT · 3D-FRONT test set, alignment loss ablationCD-S: 0.1850 -> 0.1120Improved
freeze DINO backbone during fine-tuning (ablation)Alignment-VGGT · 3D-FRONT test set, VGGT fine-tuning ablationCD-S: 0.1883 -> 0.1236Improved
also freeze frame attention layers (ablation)Alignment-VGGT · 3D-FRONT test set, VGGT fine-tuning ablationCD-S: 0.1236 -> 0.0787Improved
also freeze global attention layers (ablation)Alignment-VGGT · 3D-FRONT test set, VGGT fine-tuning ablationCD-S: 0.0787 -> 0.1120Hurt
add coarse-to-fine iterative refinementPano3DComposer · 3D-FRONT test setIoU-B: 0.5679 -> 0.5699Improved
replace differentiable optimization with feed-forward predictoralignment · 3D-FRONT test setCD-S: 0.1059 -> 0.0787Improved
replace ICP with feed-forward predictoralignment · 3D-FRONT test setCD-S: 0.2483 -> 0.0787Improved
replace SceneGen with Pano3DComposerscene composition · 3D-FRONT test setIoU-B: 0.1124 -> 0.5679Improved
replace SceneGen with Pano3DComposerscene composition · 3D-FRONT test setinference time: 63s -> 20sImproved

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