AI Paper Atlas

Research map / 3D vision / 3D generation

HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles

Yifan Wang, Francesco Pittaluga, Zaid Tasneem, Chenyu You, Manmohan Chandraker, Ziyu Jiang

CVPR 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 5 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
use Gaussian-mesh conditioning instead of colored point clouds (ablation)HorizonForge · HorizonSuite ego speed changeFID: 62.16 -> 39.92Improved
use Gaussian-mesh conditioning instead of bounding boxes (ablation)HorizonForge · HorizonSuite ego speed changeFID: 108.54 -> 39.92Improved
use video diffusion instead of single-frame Image DM (ablation)HorizonForge · HorizonSuite ego speed changeFID: 82.19 -> 39.92Improved
use video diffusion instead of Image DM (ablation)HorizonForge · HorizonSuite overallFID: 75.83 -> 33.19Improved
use Gaussian-mesh conditioning instead of point clouds (ablation)HorizonForge · HorizonSuite overallFID: 54.14 -> 33.19Improved
use HorizonForge instead of OmniRe on ego direction changeOmniRe · HorizonSuite ego direction changeFID: 80.60 -> 144.83Hurt
use HorizonForge instead of OmniRe on insertionOmniRe · HorizonSuite vehicle insertionFID: 182.29 -> 117.46Improved
use HorizonForge instead of StreetCrafter overallStreetCrafter · HorizonSuite overallFID: 91.16 -> 33.19Improved
add edited scenes with inserted vehicles to detector training3D detector · Downstream detection IoU 0.5AP: 0.0533 -> 0.0635Improved
add edited scenes with removed vehicles to detector training3D detector · Downstream detection IoU 0.7AP: 0.0103 -> 0.0134Improved
use HorizonForge instead of ReconDreamer for 6m lane shiftReconDreamer · Lane shift 6mFID: 149.19 -> 53.61Improved

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