AI Paper Atlas

Research map / 3D vision / 3D generation

Ego-1K - A Large-Scale Multiview Video Dataset for Egocentric Vision

Jae Yong Lee, Daniel Scharstein, Akash Bapat, Hao Hu, Andrew Fu, Haoru Zhao, Paul Sammut, Xiang Li, Stephen Jeapes, Anik Gupta, Lior David, Saketh Madhuvarasu and 2 more

CVPR 2026 · 3D vision › 3D generation · approach: Monocular 3D object 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
initialize 3DGS from fused stereo depth (stereo guidance)per-frame 3DGS · Ego-1K 4D NVSPSNR: 21.22 -> 29.12Improved
use stereo-guided 3DGS instead of Spacetime GaussiansSpacetime Gaussians · Ego-1K 4D NVSPSNR: 24.76 -> 29.12Improved
use dynamic radiance field K-Planes instead of per-frame 3DGSper-frame 3DGS · Ego-1K 4D NVSPSNR: 21.22 -> 16.46Hurt
use Spacetime Gaussians instead of per-frame 3DGSper-frame 3DGS · Ego-1K 4D NVSPSNR: 21.22 -> 24.76Mixed
add online calibration of camera rotations and focal lengthsEgo-1K stereo evaluation · Ego-1K stereo consistencymedian MAD: -35%Improved
choose Foundation Stereo over other stereo modelsstereo consistency · Ego-1K stereo consistencyMAD: 1.6 vs 8.0, 2.2, 1.7Mixed

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