# DachunKai/EvTexture

[ICML 2024 & TPAMI 2026] EvTexture & EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution

Repository: https://github.com/DachunKai/EvTexture
Canonical: https://ross.abutalabs.com/products/evtexture
Homepage: https://dachunkai.github.io/evtexture.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: event-camera, video-restoration, video-super-resolution, computational-photography, pytorch
Last push: 2026-06-11T18:33:51+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 8, longevity 59
- inputs: {"age_days": 837, "days_push": 83, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1207, forks 76 (observed 2026-08-28T04:03:59.498392+00:00)

## What it is
Official PyTorch implementation of EvTexture and EvTexture++, event-driven video super-resolution models that use event-camera signals to enhance texture details. Published at ICML 2024 with a TPAMI 2026 journal extension, it includes pretrained models, datasets, and a Colab demo.

## Use cases
- upscale low-resolution videos 4x with sharper textures
- use event camera data for video super-resolution
- reproduce state-of-the-art VSR results on Vid4 and REDS
- restore blurry texture regions in video frames
- research event-based vision for video restoration

## When to choose
- you have event-camera streams alongside RGB video
- you need research-grade VSR with pretrained models
- texture fidelity matters more than speed

## When to avoid
- you only have standard RGB video without event data
- you need a production-ready end-user application
- you lack a GPU for inference

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, video-processing
- domain: computer-vision, deep-learning, image-processing
- platform: python
- tags: video-super-resolution, event-camera, pytorch, video-restoration, research-code, computational-photography, video, gpu, linux, docker

## Member repositories
- DachunKai/EvTexture (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:59.498392+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 2026-08-30T06:18:57.048374+00:00, confidence not recorded.
  - readme: https://github.com/DachunKai/EvTexture (fetched 2026-08-28T04:03:59.498392+00:00, sha 61125b6a4f12)
  - homepage: https://dachunkai.github.io/evtexture.github.io/ (fetched 2026-08-29T12:26:41.992563+00:00, sha 32b716c3eadb)
- Data as of 2026-08-30T08:39:29.467469+00:00.