FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction
Wei Cao, Hao Zhang, Fengrui Tian, Yulun Wu, Yingying Li, Shenlong Wang, Ning Yu, Yaoyao Liu
摘要
Camera redirection aims to replay a dynamic scene from a single monocular video under a user-specified camera trajectory. However, large-angle redirection is inherently ill-posed: a monocular video captures only a narrow spatio-temporal view of a dynamic 3D scene, providing severely limited observations of the underlying 4D world. The key challenge is therefore to recover a complete and coherent plenoptic representation from this limited input, with consistent geometry and coherent motion. While recent diffusion-based methods achieve impressive visual generation quality, they often break down under large-angle viewpoint changes far from the original trajectory, where missing visual grounding leads to severe geometric ambiguity and temporal inconsistency. To address this, we present FreeOrbit4D, an effective training-free framework that tackles this geometric ambiguity by recovering a foreground-complete 4D proxy as structural grounding for video generation. We obtain this proxy by decoupling foreground and background reconstructions: we unproject the monocular video into a static background and partial foreground point clouds in a unified global space, then leverage an object-centric multi-view diffusion model to synthesize multi-view images and reconstruct complete foreground point clouds in canonical object space. By aligning the canonical foreground point cloud to the global scene space via dense pixel-synchronized 3D–3D correspondences and projecting the foreground-complete 4D proxy onto target camera viewpoints, we provide geometric scaffolds (e.g., depth/visibility cues) that guide a conditional video diffusion model. Extensive experiments show that FreeOrbit4D produces more faithful and temporally coherent redirected videos under challenging large-angle trajectories, and our foreground-complete 4D proxy further opens a potential avenue for practical applications such as edit propagation and 4D data generation. Project page: https://freeorbit4d.vision.ischool.illinois.edu/
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper43
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Video Diffusion ModelsJonathan Ho, Tim Salimans, Alexey A. Gritsenko, William Chan 等NeurIPS 2022 · 被引用 2,948 次
- Dynamic View Synthesis from Dynamic Monocular VideoChen Gao, Ayush Saraf, Johannes Kopf, Jia-Bin HuangICCV 2021 · 被引用 522 次
相关 Paper
- TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion ModelsMark Yu, Wenbo Hu, Jinbo Xing, Ying ShanICCV 2025 · 被引用 25 次
- Free4D: Tuning-Free 4D Scene Generation with Spatial-Temporal ConsistencyTianqi Liu, Zihao Huang, Zhaoxi Chen, Guangcong Wang 等ICCV 2025 · 被引用 3 次
- LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction ModelsMingyang Xie, Numair Khan, Tianfu Wang, Naina Dhingra 等CVPR 2026 · 被引用 10 次
- EasyCreator: Empowering 4D Creation through Video InpaintingYue Ma, Kunyu Feng, Xinhua Zhang, Hongyu Liu 等ICLR 2026 · 被引用 47 次
- Video Camera Trajectory Editing with Generative Rendering from Estimated GeometryJunyoung Seo, Jisang Han, Jaewoo Jung, Siyoon Jin 等AAAI 2026
