Anton Sochenov retweeted
Code just released: github.com/NYU-ICL/image-gs!
If you are attending #SIGGRAPH2025 in Vancouver check out our paper Image-GS, which explores various interesting aspects of compressing images and textures using 2D Gaussians.
sdiolatz.info/publications/0…
Anton Sochenov retweeted
Excited to share 2025 update from our team, including our presence at #HPG and #SIGGRAPH: community.intel.com/t5/Blogs…
We focus on visual efficiency and democratizing high-end visual experiences.
Anton Sochenov retweeted
If you happen to be at #GDC2025, I'll be giving a talk about Neural Texture Compression and Cooperative Vectors at Microsoft's Advanced Graphics Summit, feel free to attend!
schedule.gdconf.com/session/…
Anton Sochenov retweeted
Tomorrow (Tuesday) at SIGGRAPH and 11:15 am we will be demonstrating N-Dimensional Gaussian Fitting interactively and will be giving some insight into the applications and method. Join us at Exhibit Hall F for our demo!
Anton Sochenov retweeted
Check out the update from Intel Graphics Research on the recent work we are presenting at HPG and SIGGRAPH this week. New technologies and ecosystem contributions for graphics and emerging 3D GenAI field (1/n)
intel.com/content/www/us/en/…
Anton Sochenov retweeted
Looking for a fast method to render your large-scale game components?
Our lastest @HPG_Conf paper allows to render terrains, oceans and even entire planets in realtime on any modern GPU using compute shaders. Fun fact: we use a Concurrent Binary Tree as a GPU memory manager.
Anton Sochenov retweeted
We are finally releasing the code for NDG so you can train 6D Radiance Fields, 10D+ Global Illumination or use it in your own applications. We are aiming to improve the codebase over time so reach out in Denver or online!
github.com/intel/ndg-fitting…
Time to share our #SIGGRAPH2024 paper "N-Dimensional Gaussians for Fitting of High Dimensional Functions"!
We show that N-Dimensional Gaussian mixtures can be optimized to handle high dimensional inputs like MLPs with a fraction of the training times.
sdiolatz.info/ndg-fitting/
Anton Sochenov retweeted
Blender 4.2 LTS is out with the latest Intel Open Image Denoise 2.3, which significantly improves quality in High Quality + Accurate Prefilter mode, adds a new Fast Quality mode for even faster previews, enables GPU denoising for CPU renders and AMD GPU support as well. #IamIntel
Blender Foundation and the online developers community are proud to present Blender 4.2 LTS!
Packed with features and improvements ready to power your projects for the next two years.
📖 What's new: blender.org/download/release…
🧡 Donate to Blender at fund.blender.org #b3d
Anton Sochenov retweeted
Intel Open Image Denoise 2.3.0 is out! It significantly improves quality for HDR denoising w/ pre-filtering using a larger model, adds 'fast' quality mode for ~1.5-2x higher perf, Intel Arrow Lake, Lunar Lake and Battlemage GPU support, and more: github.com/RenderKit/oidn/re… #IamIntel
Anton Sochenov retweeted
Intel’s new AI image generation app is free and runs entirely on your PC
bit.ly/4aLbLlr
Anton Sochenov retweeted
Wrote a short blog with a bit of a background on why we chose to work on the problem of N-Dimensional fitting and why we think our approach is a good idea over previous work! Hope it gives some insight about our approach!
community.intel.com/t5/Blogs…
Anton Sochenov retweeted
Our I3D paper won the best paper presentation & the best paper runner-up awards. Congrats on the amazing presentation @thomasdeliot !
In our latest @I3DCONF paper, we transform any rasterizer into a differentiable one with minimal engineering and zero external dependencies.
Optimize game assets and volumes, train 3D Gaussian Splats, etc. directly within your existing engine. Compute shaders is all you need!
Anton Sochenov retweeted
PC game and performance analysis just leveled up with PresentMon 2.0! More accurate metrics, new graphing and overlay options, expanded percentile stats, and more. Follow the link to learn more and download version 2.0 today: intel.ly/3U8Cvam
Anton Sochenov retweeted
XeSS 1.3 is out today with new presets, scaling factors, and updated models to boost performance and quality.
Read more about it: intel.ly/3xp3VQk #XeSS
Anton Sochenov retweeted
For Stable Diffusion 3, we measured the training throughput for the 2B Multimodal Diffusion Transformer (MMDiT) architecture model. Gaudi 2 trained images 1.5x faster than the H100-80GB, and 3x faster than A100-80GB GPU’s when scaled up to 32 nodes. (2/3)
Anton Sochenov retweeted
Intel Open Image Denoise 2.2.0 is out! It improves image quality and CPU performance, adds support for Intel Meteor Lake GPUs, Apple GPUs (via Metal) and all ARM64 CPUs, removes dependency on CUDA Runtime (switches to Driver API), and more! github.com/OpenImageDenoise/… #IamIntel
The team of Computer Graphics Research Scientists at #Intel is hiring summer interns to work on-site on challenging problems to bring real-time path tracing one step closer to run on Intel #GPUs.
Come join us to make a difference.
intel.wd1.myworkdayjobs.com/…
4
135
Anton Sochenov retweeted
If you like to do some compute GPU work on your laptop, MTL and Linux has got you covered... Oh and Blender works with it too!
Nice work by Intel software teams to enable some of the great integrations of the Intel hardware graphics teams!
The @Intel Meteor Lake Arc Graphics: A Fantastic Upgrade, Battles AMD RDNA3 Integrated Graphics
On the Meteor Lake @IntelGraphics side, it's looking great! Competing with RDNA3 integrated in raw performance & winning in perf-per-Watt! Huge gen uplift!
phoronix.com/review/meteor-l…
Anton Sochenov retweeted
Featuring #XeSS support and built-in #IntelArc GPUs, #IntelCore Ultra processors average 39% better performance on tons of games. intel.ly/3uV3BaF
Anton Sochenov retweeted
Intel Graphics Research scientists worked on two #SIGGRAPHAsia2023 papers. Drop by Friday morning if you are in Sydney. 1. How can we make gloss perceptually better asia.siggraph.org/2023/prese… and 2. How can we extrapolate and upsample with guidance at once asia.siggraph.org/2023/prese…





















