ReLift3D/ReLift

Library

Get alerts like this View on GitHub Website Share on X

Can I trust it?

Be careful with this one.

Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change yesterday.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

Research code for ReLift, a method that lifts every pixel of a video into 3D trajectories by combining a dense 2D point tracker with a video 3D geometry model. A small transformer corrector repairs and completes the lifted trajectories. Includes a demo script, training on…

Who it's for

Computer vision researchers working on dense 3D point tracking and video geometry

How to use it

Install

bash scripts/setup.sh

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up ReLift3D/ReLift in my project. Follow its README: https://github.com/ReLift3D/ReLift. Explain each step and check it is safe before running anything.

Star curve

49From 0 to 49 stars between 12 Oct 2026 and 3 Nov 2026.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![ReLift3D/ReLift on RepoAlerts](https://repoalerts.com/badge/ReLift3D/ReLift.svg)](https://repoalerts.com/repo/ReLift3D/ReLift?ref=badge)

Share on X

code-video-model/CodeVideoModel
A research codebase for generating videos from editable Three.js scenes. It produces Three.js code from text prompts, renders proxy videos, creates reference images, and runs the MiniMax-H3 model to p
Models & inferencePython · 720 stars · +45 this week · 53 days old
NiazMorshed2007/reanimate
A Claude Code skill that records an existing animation (from a live site, screen recording, mp4, gif or Lottie file), rebuilds it in the user's code, then films the copy and compares timing, easing an
AI skillAI agentsJavaScript · 1,030 stars · +1,030 this week · 5 days old
JuneYaooo/rea-video
A command-line toolkit and agent skill that reverse-engineers videos shot by shot. It classifies each shot as live footage, AI-generated, 3D, or code-driven, extracts subtitles, transitions, camera an
AI skillCreative toolsPython · 74 stars · +74 this week · 5 days old
PSRben/VisionHOPE
PyTorch implementation of VisionHOPE, a hierarchical visual backbone built on self-referential nested learning, where memories evolve during image processing. Provides ImageNet classification, COCO de
ModelModels & inferencePython · 1,389 stars · +126 this week · 37 days old
hi3d-official/Hi3Dv1.0
Refines a coarse 3D mesh into high-resolution geometry, conditioned on a reference image of the same object. Built on the Sparc3D representation, it runs multi-pass sparse latent sampling and mesh ext
ModelModels & inferencePython · 648 stars · +162 this week · 18 days old
actionow-ai/vvv
Editable video templates built with Remotion, packaged as an Agent Skill that coding agents such as Claude Code and Codex use to place photos, write copy, render, and check short films. Includes a CLI
AI skillCreative toolsPython · 517 stars · +117 this week · 12 days old