AI Paper Atlas

Research map / 3D vision / Depth and stereo

Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos

Chengbo Yuan, Geng Chen, Li Yi, Yang Gao

ICCV 2025 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 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
set shape regularization weight alpha to 4 instead of 1 (ablation)EgoMono4D · HOI4DF1 (%): 18.2 -> 26.9Improved
add confidence mask regularization loss (ablation)EgoMono4D · HOI4DF1 (%): 23.9 -> 26.9Improved
use larger UniDepth backbone instead of UniDepth-S (ablation)EgoMono4D · HOI4DF1 (%): 23.8 -> 26.9Improved
add video adaptor blocks (ablation)EgoMono4D · HOI4DF1 (%): 25.8 -> 26.9Improved
use 3D shape regularization against UniDepth instead of relative-scale midas depth loss (ablation)EgoMono4D · HOI4DF1 (%): 26.1 -> 26.9Improved
use 3D flow/track loss instead of 2D pixel-space flow loss (ablation)EgoMono4D · HOI4DF1 (%): 26.7 -> 26.9No clear effect
add camera intrinsic consistency loss (ablation)EgoMono4D · HOI4DF1 (%): 25.2 -> 26.9Improved
use inference window Nw equal to training window of 4 (ablation)EgoMono4D · HOI4DChamfer Distance (mm): 17.9 -> 5.9Improved
increase window overlap No from 1 to 2 or 3 (ablation)EgoMono4D · HOI4DF1 (%): 27.9 -> 27.9No clear effect
lower video frame rate to fps/12 (ablation)EgoMono4D · POV-SurgeryChamfer Distance (mm): 25.5 -> 28.5Hurt
self-supervised EgoMono4D vs supervised DUSt3R-family baselines on egocentric zero-shot reconstructionEgoMono4D · POV-Surgery (zero-shot)F1 (%): 9.7 -> 13.5Improved
end-to-end self-supervised training vs modularized no-training versionEgoMono4D · HOI4DChamfer Distance (mm): 8.9 -> 5.9Improved

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