SS3D: End2End Self-Supervised 3D from Web Videos
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913123923918848 |
|---|---|
| author | Hariat, Marwane Franchi, Gianni Filliat, David Manzanera, Antoine |
| author_facet | Hariat, Marwane Franchi, Gianni Filliat, David Manzanera, Antoine |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22686 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SS3D: End2End Self-Supervised 3D from Web Videos Hariat, Marwane Franchi, Gianni Filliat, David Manzanera, Antoine Computer Vision and Pattern Recognition 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. |
| title | SS3D: End2End Self-Supervised 3D from Web Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.22686 |