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.

Excited to share the latest Mitsuba and Dr.Jit releases - packed with new features! 🚀 I’ll be at SIGGRAPH this week, happy to chat about the latest changes or anything Mitsuba-related

Wenzel Jakob@wjakob.bsky.social · last yr.

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?

🥻Our new #SIGGRAPH2025 paper introduces a novel pipeline that captures and digitizes physical threads, predicts fabric appearance from the weaving pattern, and aids designers in exploring new possibilities. 🔗 mandyxia.com/research/fabrix.html

Very happy about this release! I'll be at SIGGRAPH Asia next week if anyone wants to chat about Mitsuba/Dr.Jit in person. Also, I'm ready to take the next step in my career. So, if you work in (inverse) rendering, let's get in touch - my DMs are open 🚀 !

Wenzel Jakob@wjakob.bsky.social · 2y ago

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🧵

We are excited to present a SIGGRAPH Asia paper exploring a new application of inverse rendering to Tomographic Volumetric Additive Manufacturing (TVAM), a new light-based 3D printing technology that can print objects in less than a minute.