AI Paper Atlas

Research map / 3D vision / Gaussian splatting

FreeGen: Feed-Forward Reconstruction–Generation Co-Training for Free-Viewpoint Driving Scene Synthesis

Shijie Chen, Peixi Peng

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 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 generative refinement to reconstruction (ablation)FreeGen · nuScenes left 2m shiftFVD: 246.73 -> 60.53Improved
add generative refinement to reconstruction (ablation)FreeGen · nuScenes left 2m shiftFID: 23.25 -> 15.49Improved
add opacity map as geometry condition (ablation)FreeGen · nuScenes left 2m shiftFID: 15.49 -> 13.86Improved
add opacity map as geometry condition (ablation)FreeGen · nuScenes left 2m shiftFVD: 60.53 -> 57.21Improved
add reconstruction co-training (ablation)FreeGen · nuScenes left 2m shiftFID: 13.86 -> 14.39Hurt
add reconstruction co-training (ablation)FreeGen · nuScenes left 2m shiftFVD: 57.21 -> 54.93Improved
add generation co-training (ablation)FreeGen · nuScenes left 2m shiftFID: 13.86 -> 13.16Improved
add generation co-training (ablation)FreeGen · nuScenes left 2m shiftFVD: 57.21 -> 51.78Improved
co-train both reconstruction and generation (ablation)FreeGen · nuScenes left 2m shiftFVD: 57.21 -> 50.92Improved
use our feed-forward reconstruction geometry condition instead of image warping (ablation)FreeGen · nuScenes shift ±2mFID: 60.64 -> 20.96Improved
use our feed-forward reconstruction geometry condition instead of image warping (ablation)FreeGen · nuScenes shift ±4mFVD: 398.36 -> 370.79Improved
use reconstruction model geometry instead of image warping on recorded trajectory (ablation)FreeGen · nuScenes original trajectoryPSNR: 18.14 -> 20.40Improved

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