AI Paper Atlas

Research map / 3D vision / Depth and stereo

UFO-4D: Unposed Feedforward 4D reconstruction from Two Images

Junhwa Hur, Charles Herrmann, Songyou Peng, Philipp Henzler, Zeyu Ma, Todd Zickler, Deqing Sun

ICLR 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D 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 photometric-loss gradient to Gaussian center and velocity (full model vs w/o image gradient) (ablation)UFO-4D · Stereo4D (256x256 ablation)Point EPE: 0.903 -> 0.827Improved
add rendering losses on point and motion (full vs w/o motion and point rendering) (ablation)UFO-4D · Stereo4D (256x256 ablation)Point EPE: 0.911 -> 0.827Improved
add rendering losses on point and motion (ablation)UFO-4D · Stereo4D (256x256 ablation)PSNR: 20.675 -> 23.929Improved
add all rendering losses (point, motion, image) versus none (ablation)UFO-4D · Stereo4D (256x256 ablation)Point EPE: 0.886 -> 0.827Improved
add image gradient to Gaussian parameters (ablation)UFO-4D · Stereo4D (256x256 ablation)PSNR: 24.268 -> 23.929Hurt
use dynamic 3DGS output instead of per-pixel point and motion (ablation)UFO-4D · KITTIPoint EPE: 4.567 -> 3.553Improved
use dynamic 3DGS output instead of per-pixel point and motion (ablation)UFO-4D · Stereo4DPoint EPE: 0.809 -> 0.781Improved
use dynamic 3DGS output instead of per-pixel point and motion (ablation)UFO-4D · BonnPoint EPE: 0.196 -> 0.211Hurt
use feedforward pose head instead of PnP+RANSAC on UFO-4D (ablation)UFO-4D · Stereo4DATE: 0.0120 -> 0.0101Improved
initialize from MASt3R instead of MonST3R (ablation)UFO-4D · Stereo4D (small scale)Point EPE: 0.868 -> 0.781Improved
initialize from MASt3R instead of MonST3R (ablation)UFO-4D · Bonn (small scale)Point EPE: 0.155 -> 0.211Hurt
train on Stereo4D only instead of mixing ST/PO/VK (ablation)UFO-4D · Stereo4D (dataset mixture)PSNR: 21.918 -> 23.929Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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