ICML 2026poster0 citations

PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation

Chuanxin Song, Peixi Peng

Abstract

Panoramic video depth estimation is pivotal for applications such as Virtual Reality and World Models. However, advancements in this field are impeded by two primary obstacles: the scarcity of large-scale training data and the unique spatiotemporal challenges of Equirectangular Projection (ERP), which hinder the direct transfer of perspective models. In this paper, we first present **PanoCARLA**, a large-scale synthetic RGB-D panoramic video dataset, featuring natural motion trajectories and drone-like roaming perspectives. Building on this foundation, we propose **PVDepth**, an end-to-end framework adapted from perspective video depth models. To tackle ERP-specific geometric distortions and consequent non-linear temporal dynamics, we introduce two core mechanisms: (1) A *Progressive Sphere-aware Noise Initialization* strategy that anneals the noise distribution from planar to spherical, guiding the model to adapt to non-uniform information density; and (2) A *Cube-rectified Temporal Modeling* module that incorporates an auxiliary cubemap temporal branch to rectify non-linear temporal dynamics in the ERP domain. Extensive experiments demonstrate that PVDepth achieves superior performance, generating geometrically accurate and temporally consistent depth sequences. *Code and data will be released.*

VisionBenchmark
BibTeX
@inproceedings{
song2026pvdepth,
title={{PVD}epth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation},
author={Chuanxin Song and Peixi Peng},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=HwYgnZjxUB}
}