v2026.9.20
multimodal-art-projection/YuEv2026.9.20Sep 20, 2026by harry7557558
Upgrading?
Full Release Notes
Changelog - Support adaptive frame extraction from videos - Improved SfM for 360 cameras with rig constraints - Support warm start training from an existing 3DGS PLY file (#26) - Support presets and batch processing for dataset creation and meshing - Support specifying GPU to use for dataset creation and meshing (#76) - Support generating masks without masking feature points in dataset creation - Improved HDR training on exposure bracketed captures - Support training on RGBA images - Support specifying a fixed background color - Fixed SfM rerun when adding depth and normal maps beside a dataset in GUI - Fixed "VkResult -4" error when meshing on large models Note: - This release carries difference in SfM intended to be improvement. Please submit an issue if you notice significant regression in accuracy or speed compared to previous versions.
Related Repositories
public-apis/public-apis★ 491,231
A collective list of free APIs
NousResearch/hermes-agent★ 256,109
The agent that grows with you
yt-dlp/yt-dlp★ 200,274
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,568
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,700
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.