SEE4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
Loading...
Date
2026
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually annotated camera poses, which are labor-intensive and brittle for inthe-wild footage. Recent warp-then-inpaint approaches mitigate the need for pose labels by warping input frames along a novel camera trajectory and using an inpainting model to fill missing regions, thereby depicting the 4D scene from diverse viewpoints. However, this trajectory-to-trajectory formulation often entangles camera motion with scene dynamics and complicates both modeling and inference. We introduce SEE4D, a pose-free, trajectory-to-camera framework that replaces explicit trajectory
prediction with rendering to a bank of fixed virtual cameras, thereby separating camera control from scene modeling. A viewconditional video inpainting model is trained to learn a robust geometry prior by denoising realistically synthesized warped images and to inpaint occluded or missing regions across virtual viewpoints, eliminating the need for explicit 3D annotations. Building on this inpainting core, we design a spatiotemporal autoregressive inference pipeline that traverses virtual-camera splines and extends videos with overlapping windows, enabling coherent generation at bounded per-step complexity. We validate See4D on cross-view video generation and sparse reconstruction benchmarks. Across quantitative metrics and qualitative assessments, our method achieves superior generalization and improved performance relative to pose- or trajectory-conditioned baselines, advancing practical 4D world modeling from casual videos.
Description
CCS Concepts: Computing methodologies → Reconstruction; Appearance and texture representations;
@article{10.1111:cgf.70345,
journal = {Computer Graphics Forum},
title = {{SEE4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting}},
author = {Lu, Dongyue and Liang, Ao and Liu, Ziwei and Huang, Tianxin and Fu, Xiao and Zhao, Yuyang and Ma, Baorui and Pan, Liang and Yin, Wei and Kong, Lingdong and Ooi, Wei Tsang},
year = {2026},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70345}
}