4K4D: Real-Time 4D View Synthesis at 4K Resolution
This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recently, some methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when rendering high-resolution images. To overcome this problem, we propose 4K4D, a 4D point cloud representation that supports hardware rasterization and enables unprecedented rendering speed. Our representation is built on a 4D feature grid so that the points are naturally regularized and can be robustly optimized. In addition, we design a novel hybrid appearance model that significantly boosts the rendering quality while preserving efficiency. Moreover, we develop a differentiable depth peeling algorithm to effectively learn the proposed model from RGB videos. Experiments show that our representation can be rendered at over 400 FPS on the DNA-Rendering dataset at 1080p resolution and 80 FPS on the ENeRF-Outdoor dataset at 4K resolution using an RTX 4090 GPU, which is 30x faster than previous methods and achieves the state-of-the-art rendering quality. Our project page is available at https://zju3dv.github.io/4k4d/.
Code (0)
등록된 구현이 없습니다.
Tasks
4kGPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Quark: Real-time, High-resolution, and General Neural View Synthesis
We present a novel neural algorithm for performing high-quality, high-resolution, real-time novel view synthesis. From a sparse set of input RGB images or videos streams, our network both reconstructs the 3D scene and re…
3D geometryNovel View SynthesisPreface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis
NeRFs have enabled highly realistic synthesis of human faces including complex appearance and reflectance effects of hair and skin. These methods typically require a large number of multi-view input images, making the pr…
Camera CalibrationFace GenerationNeRFSuperGS: Super-Resolution 3D Gaussian Splatting Enhanced by Variational Residual Features and Uncertainty-Augmented Learning
Recently, 3D Gaussian Splatting (3DGS) has exceled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it faces challenges for high-resolution novel view synthesis (HRNV…
3DGSNovel View SynthesisSuper-ResolutionGeneralizable NGP-SR: Generalizable Neural Radiance Fields Super-Resolution via Neural Graph Primitives
Neural Radiance Fields (NeRF) achieve photorealistic novel view synthesis but become costly when high-resolution (HR) rendering is required, as HR outputs demand dense sampling and higher-capacity models. Moreover, naive…
Novel View SynthesisMERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale …