01Research
Qi Yang and colleagues have presented GSCV++, a lightweight pipeline that converts time-series 3DGS data into 2D maps and compresses them with existing video codecs. They report rate-distortion improvements of more than 20% for intra-frame coding and more than 60% for inter-frame coding over prior methods.
Why it mattersWhat can be confirmed from the source material is limited to the scope of the paper's abstract. If the method can use existing hardware video codecs, it may reduce the implementation burden on the device side for streaming and playback of dynamic 3DGS. However, real-device performance and image quality need to be checked in the full paper or the implementation.
Source: arxiv.orgRead more
02Research
Jiacheng Ding and colleagues have presented AbacusGS, which embeds the 3DGS drawing order in the scene layout and skips per-splat sorting. The authors report 4.5x faster rendering in an OpenGL viewer that sorts on the CPU (author-announced value).
Why it mattersFor developers who display 3DGS in web and mobile viewers, this could be an option for reducing the CPU sorting load. However, only the paper's abstract is available at this point, and the code has not been released.
Source: arxiv.orgRead more
03Robotics
NVIDIA has published on arXiv a common framework that uses its Cosmos world foundation model for real-time interactive simulation. Code and model checkpoints have also been released.
Why it mattersThis research points toward building video-generation-based virtual environments on a common foundation for training and evaluating robots and autonomous driving. It may be usable for validation before real-machine testing, but accuracy and suitability for practical use cannot be confirmed from the available material.
Source: arxiv.orgRead more
04Tools
A ComfyUI node that estimates depth, normals, albedo, Cryptomatte and other passes from a single background image and packages them into a multilayer EXR and a Nuke script has been released on GitHub. It combines open-weight models that run locally.
Why it mattersIn anime and VFX production, approved backgrounds are sometimes delivered as a single flat image. In that case, adding relighting, fog, blur or camera movement on the compositing side is difficult. RenderPasses offers a way to create compositing passes from such flat material.
Source: github.com +1 moreRead more