AI Paper Atlas

Research map / 3D vision / 3D generation

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling

Kaiyuan Tan, Yingying Shen, Ziyue Zhu, Mingfei Tu, Haohui Zhu, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye

CVPR 2026 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 4 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 recurrent scene tokens with refinement over independent clip prediction (ablation)UFO · WOD 8sPSNR: 21.25 -> 27.39Improved
add 3D-aware memory over implicit memory (ablation)UFO · WOD 8sPSNR: 26.67 -> 27.08Improved
add refinement of earlier tokens to 3D-aware memory (ablation)UFO · WOD 8sPSNR: 27.08 -> 27.39Improved
add historical scene tokens (ablation)UFO · WOD 8sPSNR: 26.31 -> 27.39Improved
add progressive training on longer sequences (ablation)UFO · WOD 8sPSNR: 20.67 -> 27.39Improved
add lifespan prediction for Gaussians (ablation)UFO · WOD 8sPSNR: 26.47 -> 27.39Improved
add bounding box guidance for dynamic objects (ablation)UFO · WOD 8sPSNR: 26.88 -> 27.39Improved
use UFO instead of STORM as sequence grows to 16s (zero-shot)UFO · WOD 16s zero-shotPSNR: 22.02 -> 27.04Improved
use UFO instead of STORM on short 2s sequencesUFO · WOD 2sDepth RMSE: 5.48 -> 5.45No clear effect
use bounding-box and lifespan dynamic modeling instead of STORM constant velocity (10 frames)UFO · WOD dynamic objects 2sPSNR: 22.92 -> 25.08Improved
visibility-based filtering instead of global attentionUFO · WOD 16s inferenceInference time: 1.47s -> 0.44sImproved

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