Research Scientist at Google. Ex rendering researcher at Weta Digital.
Zürich, Switzerland
- Tweets 46
- Following 155
- Followers 436
- Likes 86
Pinned Tweet
Ever wanted to reconstruct high-frequency directional signals or beyond?
I'm happy to finally announce our latest publication at #SIGGRAPH2026: "Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding" 🚀
2
8
27
2,237
🎙️ Last week I presented our SIGGRAPH paper "Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding"
The interactive presentation I gave is now live on our project's webpage!
📎 weiphil.github.io/portfolio/…
1
8
417
Ever wanted to reconstruct high-frequency directional signals or beyond?
I'm happy to finally announce our latest publication at #SIGGRAPH2026: "Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding" 🚀
2
8
27
2,237
with Lukas Bode, Philipp Slusallek, Adrián Jarabo, @seb_spe
#Rendering #NeuralRendering #SIGGRAPH2026
1
99
We propose to extend hash-grids to directions via a hierarchical geodesic grid, and show applications to path guiding, radiance fields & neural radiance caching. Source code and more details on our project webpage!
🔗 weiphil.github.io/portfolio/…
1
88
Weier Philippe retweeted
I am excited to announce Dr.Jit 1.4 and Mitsuba 3.9 which now feature GPU-accelerated compute/ray tracing on Apple Silicon. Significant optimizations in both projects accelerate tracing/code generation ~2x. They generate better code and have faster Python bindings.🧵
1
8
70
6,026
Weier Philippe retweeted
I'm excited to share the open-source release of hdMitsuba, a USD Hydra delegate for the Mitsuba 3 renderer.
Using USD's Hydra API, this project brings Mitsuba directly into OpenUSD workflows. The GIF below shows interactive rendering within usdview. 🧵
1
5
20
1,653
Are you at #SIGGRAPH, and like inverse rendering as much as I do? Come to our talk on "Practical Inverse Rendering of Textured and Translucent Appearance" at 14:40 during the Light & Relight session! Perfect opportunity to catch up if you come by our poster later as well 🚀
3
31
1,602
🚀 The source code for our #SIGGRAPH2025 paper "Practical Inverse Rendering of Textured and Translucent Appearance" is now available!
🔗 GitHub: github.com/google/practical-…
35
133
6,356
Inverse rendering has become a standard tool for 3D reconstruction problems. However, recovering high-frequency appearance textures is challenging. In our SIGGRAPH 2025 paper, we propose several techniques to robustly reconstruct complex appearances (e.g., human skin). 1/n
2
40
348
16,559
Finally, our methods enable high-quality facial appearance reconstruction from sparse captures. We fit parameters of standard production rendering models, producing realistic results without neural rendering. 5/n
1
5
704
For PDF, supplemental and high-quality videos, check out the project webpage at weiphil.github.io/portfolio/…! Joint work with Jérémy Riviere, Ruslan Guseinov, Stephan Garbin, Philipp Slusallek, @bernd_bickel, Thabo Beeler and @DelioVicini #SIGGRAPH2025 n/n
6
716
If you are at SIGGRAPH, come check out the live demo of our paper "N-BVH: Neural ray queries with bounding volume hierarchies" in the Emerging Technology session from 11:15-1:15 pm in Exhibit Hall F!
1
10
74
5,023
Weier Philippe retweeted
Our work on #NBVH (Neural ray queries with Bounding Volume Hierarchies) will be presented this summer at #SIGGRAPH2024!
What's that? See🧵below ⤵️
📃Source Code: github.com/WeiPhil/nbvh
🌐Project Page/Paper: weiphil.github.io/portfolio/…
(ft. @PhilippeWeier @iliyang @boubek et al.)
1
7
23
1,874
We added binary releases for some GPUs to our N-BVH implementation🚀No more lengthy compilation just to try out rendering your own scene in our framework! Check it out here: github.com/WeiPhil/nbvh/rele…
2
14
71
6,660
Ever wanted to load a large asset in your GPU path tracer, only to find it doesn't fit in memory? Then check out our #SIGGRAPH2024 paper “N-BVH: Neural ray queries with bounding volume hierarchies” (with Alexander Rath, @exppad, @iliyang, Philipp Slusallek and @boubek)
3
42
160
18,486
Our N-BVH combines a traditional BVH with a hash-grid encoding to serve neural ray queries and integrate seamlessly into ray-tracing pipelines. Trained in a couple of minutes and running inference in real-time, our representation achieves up to 42x compression on complex assets.
2
11
908
For more details, check out the project's webpage weiphil.github.io/portfolio/… and our source code at github.com/WeiPhil/nbvh !
2
11
32
3,187