Efficient 4D Gaussian Stream with Low Rank Adaptation
Not on the map. Why?
Abstract (arXiv)
Recent methods have made significant progress in synthesizing novel views with long video sequences. This paper proposes a highly scalable method for dynamic novel view synthesis with continual learning. We leverage the 3D Gaussians to represent the scene and a low-rank adaptation-based deformation model to capture the dynamic scene changes. Our method continuously reconstructs the dynamics with chunks of video frames, reduces the streaming bandwidth by 90% while maintaining high rendering quality comparable to the off-line SOTA methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 22 references that are in the map. First posted on arXiv 23 Feb 2025.
Builds on
18 of 22 references.
References · 18
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
- 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
- 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
- 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
- 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
- 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
- 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 173
- 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
6 more
- 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
- 2022Mixed Neural Voxels for Fast Multi-view Video Synthesiscited by 126
- 2024Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splattingcited by 104
- 2023Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fieldscited by 59
- 2023INV: Towards Streaming Incremental Neural Videoscited by 7
- 2024CD-NGP: A Fast Scalable Continual Representation for Dynamic Scenescited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.