DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to turn a casual clip into a 24-view orbit set with 4DAnyone

Generate 24 consistent target-view videos of one person from a single monocular video.

  • Top pick
  • Research
  • Intermediate
  • 1 hour
  • From the README
  • Any agent

Authorization notice. 4DAnyone is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA researcher or developer preparing multiview training data for 4D Gaussian Splatting when they only have one casual video of a person.

The problemMultiview capture of a person needs many synchronized cameras, which most people do not have.

The outcomeA folder with cameras.json, pose skeleton videos, and 24 target videos covering a full 360 degree orbit.

What you need first

  • A CUDA-capable NVIDIA GPU (README cites peak use below 24 GB and an RTX 4090 benchmark)
  • Git and conda installed
  • A source video that is a single person, 1080p or higher, 9:16 portrait, at least 121 frames
  • Permission to use the person shown in the source video

Steps

  1. git clone https://github.com/ant-research/4DAnyone.git
  2. cd 4DAnyone
  3. git submodule update --init third_party/GVHMR
  4. conda create -n 4danyone python=3.11 -y then conda activate 4danyone
  5. pip install -r requirements.txt
  6. python inference.py --video_path "data/source/pexels/2785536-uhd_2160_3840_25fps.mp4" --output_dir "data/fdanyone/pexels/2785536-uhd_2160_3840_25fps" --views_per_layer 24 (inferred, check the README)

Prompt for your agent

In the 4DAnyone repo, replace the example video path with <video_path> and run inference.py with --views_per_layer 24 writing to <output_dir>. Expected output: cameras.json, skeletons/, and videos/ with 24 target videos. Verify that cameras.json lists 24 views and videos/ contains 24 .mp4 files.

Caveat. The README asks for a 121-frame, 1080p or higher, 9:16 single-person video and notes that inference averages about 27 seconds per 121-frame video on one RTX 4090.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page