# apchenstu/TensoRF

[ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

Repository: https://github.com/apchenstu/TensoRF
Canonical: https://ross.abutalabs.com/products/tensorf
Language: Python
License: MIT
License Family: permissive
Topics: 3d-reconstruction, 3d-modelling, 3d-rendering
Last push: 2025-06-19T20:12:47+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 27, release rhythm 35, longevity 100
- inputs: {"age_days": 1630, "days_push": 440, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1239, forks 156 (observed 2026-08-28T04:04:06.055067+00:00)

## What it is
TensoRF is a PyTorch implementation of the ECCV 2022 paper 'TensoRF: Tensorial Radiance Fields', which models and reconstructs radiance fields using tensor decomposition (VM and CP). It offers fast training, compact memory footprint, and state-of-the-art novel view synthesis quality, with mesh export support.

## Use cases
- reconstruct 3d scenes from images
- novel view synthesis from photos
- train a radiance field on NeRF datasets
- render images from a pretrained checkpoint
- export a mesh from a trained radiance field
- compare VM and CP tensor decomposition for radiance fields

## When to choose
- you need fast NeRF-style training with low memory usage
- you want high-quality novel view synthesis on standard datasets like Synthetic-NeRF, NSVF, Tanks&Temples, or LLFF
- you need to extract meshes from radiance fields
- you want a research baseline for tensor-based radiance field methods

## When to avoid
- you need real-time rendering on consumer hardware without a GPU
- you want a production-ready 3D reconstruction pipeline with a GUI
- you need dynamic or time-varying scenes (TensoRF targets static scenes)
- you prefer Gaussian splatting or mesh-based reconstruction workflows

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, graphics, simulation
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python
- tags: radiance-fields, neural-rendering, 3d-reconstruction, novel-view-synthesis, tensor-decomposition, pytorch, eccv-2022, linux, gpu

## Member repositories
- apchenstu/TensoRF (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:06.055067+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:09:56.210864+00:00, confidence not recorded.
  - readme: https://github.com/apchenstu/TensoRF (fetched 2026-08-28T04:04:06.055067+00:00, sha dfdb3ad3970b)
- Data as of 2026-08-30T08:39:29.467469+00:00.