@mrnerf.bsky.social
The two most popular 3D Gaussian Splatting repositories on GitHub! Okay, there's no way to reach first place. :)
March 16, 2025 at 7:13 PM
The two most popular 3D Gaussian Splatting repositories on GitHub! Okay, there's no way to reach first place. :)
**HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting**
December 6, 2024 at 7:58 AM
**HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting**
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos
December 6, 2024 at 7:43 AM
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos
Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
Abstract:
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on sparse voxels without neural networks or 3D Gaussians.
Abstract:
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on sparse voxels without neural networks or 3D Gaussians.
December 6, 2024 at 7:34 AM
Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
Abstract:
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on sparse voxels without neural networks or 3D Gaussians.
Abstract:
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on sparse voxels without neural networks or 3D Gaussians.
Monocular Dynamic Gaussian Splatting is Fast and Brittle but Smooth Motion Helps
Abstract (excerpt):
The fast pace of work in this area has produced multiple simultaneous papers that claim to work best, which cannot all be true.
Abstract (excerpt):
The fast pace of work in this area has produced multiple simultaneous papers that claim to work best, which cannot all be true.
December 6, 2024 at 7:29 AM
Monocular Dynamic Gaussian Splatting is Fast and Brittle but Smooth Motion Helps
Abstract (excerpt):
The fast pace of work in this area has produced multiple simultaneous papers that claim to work best, which cannot all be true.
Abstract (excerpt):
The fast pace of work in this area has produced multiple simultaneous papers that claim to work best, which cannot all be true.
Hot take: Pose estimation methods should generally be evaluated using a baseline training method, such as 3D Gaussian Splatting, to assess novel-view synthesis quality.
December 5, 2024 at 1:30 PM
Hot take: Pose estimation methods should generally be evaluated using a baseline training method, such as 3D Gaussian Splatting, to assess novel-view synthesis quality.