reconstructing different angles from live footage
Summary
4D Gaussian Splatting is a technique that converts flat 2D images into three-dimensional spatial data, enabling reconstruction of different angles from live footage.
Similar Articles
VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors
VidSplat is a training-free generative reconstruction framework that uses video diffusion priors to recover complete 3D scenes from sparse inputs by synthesizing novel views.
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.
ZipSplat: Fewer Gaussians, Better Splats
ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.
Gaussian Splat of a Strawberry
A Gaussian splat of a strawberry, created from 90 perspectives with focus stacking, using slang-splat for training and SuperSplat for viewing.
3D Gaussian Splatting in a Weekend
A tutorial on building a simplified 3D Gaussian splatting renderer from scratch in C++ and OpenGL, covering loading and rendering Gaussian splats.