AI Paper Atlas

Research map / 3D vision / Depth and stereo

OmniX: Any-view and Any-time 4D reconstruction via Feed-forward Trajectory Fields

Yanqin Jiang, Tengfei Wang, Zhenwei Wang, Chenjie Cao, Junta Wu, Wenhan Luo, Weiming Hu, Jin Gao, Chunchao Guo

ECCV 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 3 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 proposed temporal embedding instead of AdaLN (ablation)OmniX SSA · SSA ablation monocularFG APD3D: 0.260 -> 0.293Improved
use proposed temporal embedding instead of AdaLN (ablation)OmniX SSA · SSA ablation hybridFG APD3D: 0.291 -> 0.324Improved
add self attention among dynamic tokens (ablation)OmniX SSA · SSA ablation monocularFG APD3D: 0.297 -> 0.293No clear effect
add self attention among dynamic tokens (ablation)OmniX SSA · SSA ablation disjoint and hybridFG APD3D: 0.298 -> 0.298; 0.324 -> 0.324No clear effect
add cross attention (ablation)OmniX SSA · SSA ablation monocularFG APD3D: 0.171 -> 0.297Improved
add cross attention (ablation)OmniX SSA · SSA ablation disjointFG APD3D: 0.197 -> 0.298Improved
add cross attention (ablation)OmniX SSA · SSA ablation hybridFG APD3D: 0.205 -> 0.324Improved
add sparse design (ablation)OmniX · 16-frame efficiencyRuntime (s): 4.10 -> 2.15Improved
add sparse design (ablation)OmniX · 16-frame efficiencyFLOPs (T): 15.25 -> 12.07Improved
increase top-rho percent of dynamic tokens from 10 to 30 (ablation)OmniX · 4-frame monocularAPD3D: 0.3194 -> 0.3454Improved
increase training data size (ablation)OmniX · 16-frame monocularAPD3D: 0.182 -> 0.243Improved
train with large camera motion data and disentangle dynamicsOmniX versus VDPM · Dense trajectories, disjoint pairs (first frame)FG APD3D: 0.164 -> 0.322Improved

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