SS3D: End2End Self-Supervised 3D from Web Videos

SS3D pretrains a feed-forward monocular 3D estimator via web-scale SfM self-supervision, achieving strong zero-shot cross-domain depth, ego-motion, and intrinsics prediction.

Marwane Hariat, Gianni Franchi, David Filliat, Antoine Manzanera

Published 2026Paris Poster Session 3 · Thu, Dec 10, 12:30 PM–2:30 PM local time · Paris Poster HallarXiv ↗OpenReview ↗

70%

OverallHighly rated

OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel5/20reviewers recommend it

lenient 3/5

medium 2/10

strict 0/5

AI panel?Vote to see what the 20 AI reviewers said

Abstract

We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly predicts depth, ego-motion, and intrinsics in a single forward pass and is trained/evaluated as a coherent end-to-end 3D estimator. To stabilize joint learning, we use an intrinsics-first two-stage schedule and a unified single-checkpoint evaluation protocol. Scaling SfM self-supervision to unconstrained web video is challenging due to weak multi-view observability and strong corpus heterogeneity; we address these with a multi-view signal proxy (MVS) used for filtering and curriculum sampling, and with expert training distilled into a single student. Pretraining on YouTube-8M (~100M frames after filtering) yields strong cross-domain zero-shot transfer and improved fine-tuning performance over prior self-supervised baselines. We release the pretrained checkpoint and code.