Time-Archival Camera Virtualization for Sports and Visual Performances
Yunxiao Zhang, William Stone, Suryansh Kumar

TL;DR
This paper introduces a neural volume rendering approach for camera virtualization that enables high-quality, temporally coherent novel view synthesis of dynamic scenes, supporting efficient time-archival for sports and performances.
Contribution
It proposes modeling dynamic scenes with rigid transformations and neural representations, allowing retrospective view synthesis and overcoming limitations of existing 3D Gaussian Splatting methods.
Findings
Supports time-archival for dynamic scenes
Achieves high-quality, coherent novel view synthesis
Handles large, rapid, non-rigid motions effectively
Abstract
Camera virtualization -- an emerging solution to novel view synthesis -- holds transformative potential for visual entertainment, live performances, and sports broadcasting by enabling the generation of photorealistic images from novel viewpoints using images from a limited set of calibrated multiple static physical cameras. Despite recent advances, achieving spatially and temporally coherent and photorealistic rendering of dynamic scenes with efficient time-archival capabilities, particularly in fast-paced sports and stage performances, remains challenging for existing approaches. Recent methods based on 3D Gaussian Splatting (3DGS) for dynamic scenes could offer real-time view-synthesis results. Yet, they are hindered by their dependence on accurate 3D point clouds from the structure-from-motion method and their inability to handle large, non-rigid, rapid motions of different subjects…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Advanced Vision and Imaging · 3D Shape Modeling and Analysis
