BREAKING NEWS
LATEST POSTS
-
Open Source OpenVDB Version 9.0.0 Available Now and Introduces GPU Support
First introduced in 2012, nowadays OpenVDB is commonly applied in simulation tools such as Houdini, EmberGen, Blender, and used in feature film production for creating realistic volumetric images. This format, however, lacks the GPUs support and can not be applied in games due to the considerable file size (on average at least a few Gigabytes) and computational effort required to render 3D volumes.
Volumetric data has numerous important applications in computer graphics and VFX production. It’s used for volume rendering, fluid simulation, fracture simulation, modeling with implicit surfaces, etc. However, this data is not so easy to work with. In most cases volumetric data is represented on spatially uniform, regular 3D grids. Although dense regular grids are convenient for several reasons, they have one major drawback – their memory footprint grows cubically with respect to grid resolution.
OpenVDB format, developed by DreamWorksAnimation, partially solves this issue by storing voxel data in a tree-like data structure that allows the creation of sparse volumes. The beauty behind this system is that it completely ignores empty cells, which drastically decreases memory and disk usage, simultaneously making the rendering of volumes much faster.
www.aswf.io/blog/project-update-openvdb-version-9-0-0-available-now-introduces-gpu-support/
github.com/AcademySoftwareFoundation/openvdb/releases/tag/v9.0.0
-
Open source resources for down sampling point cloud meshes
MeshLab
www.heritagedoc.pt/doc/Meshlab_Tutorial_iitd.pdfInstant Meshes
www.blendernation.com/2015/11/16/instant-meshes-a-free-qaud-based-autoretopology-program/github.com/wjakob/instant-meshes
igl.ethz.ch/projects/instant-meshes/
Open3D
www.open3d.org/docs/release/index.html
www.open3d.org/docs/release/tutorial/geometry/pointcloud.htmlPoint Cloud Utils
awesomeopensource.com/project/fwilliams/point-cloud-utilsMathWorks pcdownsample
www.mathworks.com/help/vision/ref/pcdownsample.htmlNot Open Source
Various software
cmacvfx.com/how-to-decimate-lidar-or-photogrammetry/ -
Autodesk announces acquisition of cloud-based animation pipeline software LoUPE from Tangent Labs
adsknews.autodesk.com/news/acquisition-software-from-tangent-labs
Autodesk is acquiring LoUPE, the powerful cloud-based production pipeline technology for artists and studios, and the team that created it.
Tangent Labs founder Jeff Bell will be joining Autodesk with his development team.
-
Peter Jackson Selling Weta Digital’s VFX Tech Division to Unity for $1.625 Billion
https://www.fxguide.com/fxfeatured/unity-weta-deal/
variety.com/2021/digital/news/unity-acquires-weta-digital-1235107544/
Under the deal, Unity is obtaining the Weta Digital suite of VFX tools and technology and its team of 275 engineers, who will join Unity’s Create Solutions division.
Joe Marks, Weta’s chief technology officer, will join Unity as CTO of Weta Digital.
Weta Digital’s VFX and animation teams will continue to exist as a standalone entity, known as WetaFX, which is expected to become Unity’s largest customer in the media and entertainment space. WetaFX, with about 1,700 employees, will remain majority-owned by Jackson and led by CEO Prem Akkaraju. The proposed deal is expected to close before the end of 2021, subject to regulatory approvals.
FEATURED POSTS
-
AI and the Law – Disney, NBCU sue Midjourney over copyright infringement
https://www.axios.com/2025/06/11/disney-nbcu-midjourney-copyright
Why it matters: It’s the first legal action that major Hollywood studios have taken against a generative AI company.
The complaint, filed in a U.S. District Court in central California, accuses Midjourney of both direct and secondary copyright infringement by using the studios’ intellectual property to train their large language model and by displaying AI-generated images of their copyrighted characters.
-
DiffusionLight: HDRI Light Probes for Free by Painting a Chrome Ball
https://diffusionlight.github.io/
https://github.com/DiffusionLight/DiffusionLight
https://github.com/DiffusionLight/DiffusionLight?tab=MIT-1-ov-file#readme
https://colab.research.google.com/drive/15pC4qb9mEtRYsW3utXkk-jnaeVxUy-0S
“a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. However, these approaches often struggle with real-world, uncontrolled settings due to the limited diversity and size of their datasets. To address this problem, we leverage diffusion models trained on billions of standard images to render a chrome ball into the input image. Despite its simplicity, this task remains challenging: the diffusion models often insert incorrect or inconsistent objects and cannot readily generate images in HDR format. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR difusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.”
