Results 11 to 20 of about 168,620 (333)
3D Gaussian Splatting for Real-Time Radiance Field Rendering [PDF]
ACM Transactions on Graphics, 2023 Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster ...
Bernhard Kerbl +3 more
semanticscholar +1 more source
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields [PDF]
Computer Vision and Pattern Recognition, 2021 Though neural radiance fields (NeRF) have demon-strated impressive view synthesis results on objects and small bounded regions of space, they struggle on “un-bounded” scenes, where the camera may point in any di-rection and content may exist at any ...
J. Barron +4 more
semanticscholar +1 more source
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields [PDF]
IEEE International Conference on Computer Vision, 2021 The rendering procedure used by neural radiance fields (NeRF) samples a scene with a single ray per pixel and may therefore produce renderings that are excessively blurred or aliased when training or testing images observe scene content at different ...
J. Barron +5 more
semanticscholar +1 more source
TensoRF: Tensorial Radiance Fields [PDF]
European Conference on Computer Vision, 2022 We present TensoRF, a novel approach to model and reconstruct radiance fields. Unlike NeRF that purely uses MLPs, we model the radiance field of a scene as a 4D tensor, which represents a 3D voxel grid with per-voxel multi-channel features.
Anpei Chen +4 more
semanticscholar +1 more source
Plenoxels: Radiance Fields without Neural Networks [PDF]
Computer Vision and Pattern Recognition, 2021 We introduce Plenoxels (plenoptic voxels), a systemfor photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics.
Alex Yu +5 more
semanticscholar +1 more source
Nerfstudio: A Modular Framework for Neural Radiance Field Development [PDF]
International Conference on Computer Graphics and Interactive Techniques, 2023 Neural Radiance Fields (NeRF) are a rapidly growing area of research with wide-ranging applications in computer vision, graphics, robotics, and more. In order to streamline the development and deployment of NeRF research, we propose a modular PyTorch ...
Matthew Tancik +12 more
semanticscholar +1 more source
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance [PDF]
Computer Vision and Pattern Recognition, 2023 We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions. Our model uses planes to represent a d-dimensional scene, providing a seamless way to go from static (d = 3) to dynamic (d= 4) scenes.
Sara Fridovich-Keil +4 more
semanticscholar +1 more source
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction [PDF]
Computer Vision and Pattern Recognition, 2021 We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses.
Cheng Sun, Min Sun, Hwann-Tzong Chen
semanticscholar +1 more source
Compact 3D Gaussian Representation for Radiance Field [PDF]
Computer Vision and Pattern Recognition, 2023 Neural Radiance Fields (NeRFs) have demonstrated re-markable potential in capturing complex 3D scenes with high fidelity. However, one persistent challenge that hin-ders the widespread adoption of NeRFs is the computational bottleneck due to the ...
J. Lee +4 more
semanticscholar +1 more source
pixelNeRF: Neural Radiance Fields from One or Few Images [PDF]
Computer Vision and Pattern Recognition, 2020 We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields [27] involves optimizing the representation to every ...
Alex Yu +3 more
semanticscholar +1 more source