Differentiable rendering has transformed graphics and 3D vision, but what about other fields? Our SIGGRAPH 2025 introduces misuka, the first fully-differentiable path tracer for acoustics.

How can one reconstruct the complete 3D interior of a wood block using only photos of its surfaces? 🪵
At SIGGRAPH'25 (Thursday!), Maria Larsson will present *Mokume*: a dataset of 190 diverse wood samples and a pipeline that solves this inverse texturing challenge. 🧵👇

My lab will be recruiting at all levels. PhD students, postdocs, and a research engineering position (worldwide for PhD/postdoc, EU candidates only for the engineering position). If you're at SIGGRAPH, I'd love to talk to you if you are interested in any of these.

Wow, this is such a cool paper! Basically with a surprisingly small modification to existing NeRF optimization, this paper gets a really good direct surface reconstruction technique that doesn't require all of the usual mess that meshing a NeRF requires (raymarching, marching cubes, etc).

Methods like NeRF and Gaussian Splats model the world as radioactive fog, rendered using alpha blending. This produces great results.. but are volumes the only way to get there?🤔 Our new SIGGRAPH'25 paper directly reconstructs surfaces without heuristics or regularizers.

Dr.Jit+Mitsuba just added support for fused neural networks, hash grids, and function freezing to eliminate tracing overheads. This significantly accelerates optimization &realtime workloads and enables custom Instant NGP and neural material/radiosity/path guiding projects. What will you do with it?

𝐎𝐯𝐞𝐫𝐩𝐫𝐢𝐧𝐭𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝐓𝐨𝐦𝐨𝐠𝐫𝐚𝐩𝐡𝐢𝐜 𝐕𝐨𝐥𝐮𝐦𝐞𝐭𝐫𝐢𝐜 𝐀𝐝𝐝𝐢𝐭𝐢𝐯𝐞 𝐌𝐚𝐧𝐮𝐟𝐚𝐜𝐭𝐮𝐫𝐢𝐧𝐠

Imagine 3D printing directly onto an object that already exists.

With Tomographic Volumetric Additive Manufacturing (TVAM), we can now print over existing components, opening up a world of possibilities for multi-component devices.

The latest development version of Dr.Jit now provides built-in support for evaluating and training MLPs (including fusing them into rendering workloads). They compile to efficient Tensor Core operations via NVIDIA's Cooperative Vector extension. Details: drjit.readthedocs.io/en/latest/nn...

3D Gaussian splatting relies on depth-sorting of splats, which is costly and prone to artifacts (e.g., "popping"). In our latest work, "StochasticSplats", we replace sorted alpha blending by stochastic transparency, an unbiased Monte Carlo estimator from the real-time rendering literature.

Differentiable physically-based rendering has fascinating applications outside of traditional computer graphics. This collaboration between the RGL and LAPD groups at EPFL co-led by Baptiste Nicolet and Felix Wechsler demonstrates how to use it to create complex 3D prints very quickly.

Following over 1.5 years of hard work (w/@njroussel.bsky.social &@rtabbara.bsky.social), we just released a brand-new version of Dr.Jit (v1.0), my lab's differentiable rendering compiler along with an updated Mitsuba (v3.6). The list of changes is insanely long—here is what we're most excited about🧵

ドイツ人は休めば休むほど成果を出せます👌

My team RGL is looking for new PhD students starting 2025. If you are excited about topics like inverse rendering, compilers for graphics, and physically based modeling then please join us at EPFL. Info about the lab & admission process: rgl.epfl.ch/pages/jobs (Deadline: Dec 15)