Panoptic Studio

Select parameters to load videos
← Back to Main Page
Evaluation on the CMU Panoptic Studio dataset [4]. We compare our method against SOTA dynamic monocular reconstruction methods: (i) optimization-based methods HiMoR [1] and OriGS [2], (ii) generative-based Cog-NVS [3]. The top video depicts the pre-scan and dynamic sequences on which all the models are trained on. Each row contains renders of all methods on a specific test camera alongside with the ground-truth.
Our method drastically outperforms the baselines in maintaining a consistent object geometry and sharp appearance, while accurately modeling the scene dynamics.

Training Video

Show Pre-scan
Pre-scan + Dynamic Sequence

Results

[1] Yiming Liang, Tianhan Xu, Yuta Kikuchi. HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation, CVPR 2025

[2] Junyi Wu, Jiachen Tao, Haoxuan Wang, Gaowen Liu, Ramana Rao Kompella, Yan Yan. Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos, NeurIPS 2025

[3] Kaihua Chen*, Tarasha Khurana*, Deva Ramanan. Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos, NeurIPS 2025

[4] Hanbyul Joo, Hao Liu, Lei Tan, Lin Gui, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, Yaser Sheikh. Panoptic Studio: A Massively Multiview System for Social Motion Capture, ICCV 2015