Prepared optimization inputs and selected generated object assets for the 18 HO3D training sequences used in the AGILE experiments. Code repository: https://github.com/aim-uofa/AGILE (code publication is staged separately). ho3d/preprocessed/SCENE.tar.gz: RGB/depth, masks, WiLoR predictions, hand alignment, object initialization and the actual optimization input mesh. ho3d/generated/SCENE.tar.gz: selected generated object mesh, material and texture, kept separate from the optimization representation. ho3d/initialization/SCENE.tar.gz: required 2D WiLoR joints for the eight aligned-format sequences; extract alongside the corresponding preprocessed archive. The downloader includes these…
Independent publisher
Jin-Chuan Shi
Chrisss
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers2
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image to 3d.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.