Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.11543 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908881663295488 |
|---|---|
| author | Huang, Tingxuan Zhu, Haowei Yong, Jun-hai Pan, Hao Wang, Bin |
| author_facet | Huang, Tingxuan Zhu, Haowei Yong, Jun-hai Pan, Hao Wang, Bin |
| contents | Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene modeling often rely on per-frame optimization, which can overfit to instantaneous states instead of capturing underlying motion dynamics. To address this, we present Mango-GS, a multi-frame, node-guided framework for high-fidelity 4D reconstruction. Mango-GS leverages a temporal Transformer to model motion dependencies within a short window of frames, producing temporally consistent deformations. For efficiency, temporal modeling is confined to a sparse set of control nodes. Each node is represented by a decoupled canonical position and a latent code, providing a stable semantic anchor for motion propagation and preventing correspondence drift under large motion. Our framework is trained end-to-end, enhanced by an input masking strategy and two multi-frame losses to improve robustness. Extensive experiments demonstrate that Mango-GS achieves state-of-the-art reconstruction quality and real-time rendering speed, enabling high-fidelity reconstruction and interactive rendering of dynamic scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11543 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting Huang, Tingxuan Zhu, Haowei Yong, Jun-hai Pan, Hao Wang, Bin Computer Vision and Pattern Recognition Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene modeling often rely on per-frame optimization, which can overfit to instantaneous states instead of capturing underlying motion dynamics. To address this, we present Mango-GS, a multi-frame, node-guided framework for high-fidelity 4D reconstruction. Mango-GS leverages a temporal Transformer to model motion dependencies within a short window of frames, producing temporally consistent deformations. For efficiency, temporal modeling is confined to a sparse set of control nodes. Each node is represented by a decoupled canonical position and a latent code, providing a stable semantic anchor for motion propagation and preventing correspondence drift under large motion. Our framework is trained end-to-end, enhanced by an input masking strategy and two multi-frame losses to improve robustness. Extensive experiments demonstrate that Mango-GS achieves state-of-the-art reconstruction quality and real-time rendering speed, enabling high-fidelity reconstruction and interactive rendering of dynamic scenes. |
| title | Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.11543 |