Aaron Lefohn
@aaronlefohn
Followers
4K
Following
572
Statuses
967
Vice President of Graphics Research at NVIDIA. Opinions are my own.
Joined June 2011
RT @wenzeljakob: If you try to optimize geometry using a differentiable renderer, there is an elephant in the room: geometry causes discont…
0
58
0
RT @wenzeljakob: The free web version of "Physically Based Rendering: From Theory To Practice" is now based on the 4th edition of the book.…
0
277
0
RT @mmalex: so excited by the explosion of gaussian splatting; cant wait for the community to start playing with painterly styles; on dream…
0
86
0
RT @DaqiLin: Our new conditional resampled importance sampling (CRIS) opens up possibilities for designing resampling algorithms where mar…
0
8
0
This great foundational advancement in ReSTIR now enables reuse of sub-paths. Our theory research directly targets the needs of real-time rendering.
Thrilled to announce our work "Conditional Resampled Importance Sampling and ReSTIR" (SIGGRAPH Asia 2023). We extend RIS and ReSTIR into conditional probability spaces, enabling novel forms of sample reuse. 1/7
0
11
65
RT @NVIDIAAIDev: Differentiable Slang easily integrates with existing codebases—from #Python, PyTorch, and #CUDA to HLSL. Here we introdu…
0
2
0
RT @NVIDIAAIDev: New #NVIDIAResearch paper: SLANG.D: Fast, Modular and Differentiable Shader Programming: shows how a single language serve…
0
41
0
RT @TangentVector: The Slang project is seeking experienced GPU/graphics/AI compiler programmers who want to be part of the development of…
0
16
0
RT @marcosalvi: I have been working with machine learning in graphics for a few years now and SLANG.D is the tool I wished I had from the s…
0
28
0
RT @BartWronsk: Some awesome work of my teammates on differentiable shading language, compatible with HLSL, and interoperable with CUDA/Pyt…
0
51
0
RT @csyonghe: Bringing autodiff to shaders is a challenging task. It takes years of effort to design the language that integrates different…
0
7
0
Slang is now fully differentiable. Generate PyTorch plugins from shader code. Create rendering algorithms using appearance-based optimization. Build differentiable renderers using your current shader codebase. DiffSlang connects real-time rendering and learning.
Slang is an open-source, cross-platform shading language that targets D3D, Vulkan, GLSL, CUDA and C++. Today, it is fully differentiable, which means you can autodiff your existing shader code!
0
3
41
0
17
0
Fantastic collaboration with @FidlerSanja's team. Working together to improve the quality of geometry extracted with inverse rendering.
Excited to share our #SIGGRAPH2023 project for better mesh extraction in learning & reconstruction pipelines. Project page: Joint work w/ @yoslber Jon Hasselgren @kangxue_yin @zianwang97 @ChenWenzheng @ZGojcic @FidlerSanja @nmwsharp @JunGao33210520 (1/n)
0
0
6
RT @kayvonf: 🎾 Haotian's AI tennis players are back... in 3D. 🎾 AI characters learn to play full 3D simulated tennis points by watching pr…
0
9
0
RT @jankautz: Honored to see that our work on Precomputed Radiance Transfer (2002) made it onto the SIGGRAPH Seminal Graphics Papers list:…
0
14
0
RT @SebAaltonen: The FlexiCubes technique by Nvidia (Flexible Isosurface Extraction for Gradient-based Mesh Optimization) seems very promis…
0
39
0
Buildings graphics systems for RL is an opportunity to completely rethink graphics system design.
Why does RL need large-scale computing resources? Spoiler: it can get by with a lot less! Stanford's Madrona project is an ECS-based game engine that runs 10,000s of environments in parallel on a single GPU, reducing training from hours to minutes. 1/
1
1
4