DSaurus/Tensor4D
This is the official implementation of Tensor4D: Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering.
Tensor4D helps visual effects artists, game developers, or animators create realistic, dynamic 3D scenes and animations from video footage. It takes either multiple camera views or even just a single video clip of a moving subject and produces a high-fidelity 4D (3D + time) representation. This allows for new camera angles, slow-motion effects, or integration into virtual environments.
228 stars. No commits in the last 6 months.
Use this if you need to reconstruct and render complex, dynamic real-world objects or performances in 3D from video, especially with limited camera setups.
Not ideal if your primary goal is static 3D model creation without temporal dynamics, or if you require real-time performance on typical consumer hardware.
Stars
228
Forks
11
Language
Python
License
MIT
Category
Last pushed
Jun 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DSaurus/Tensor4D"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
nerfstudio-project/nerfstudio
A collaboration friendly studio for NeRFs
google/nerfies
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.
SuLvXiangXin/zipnerf-pytorch
Unofficial implementation of ZipNeRF
yashbhalgat/HashNeRF-pytorch
Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives:...