NVIDIA Instant NeRF (Neural Radiance Field), the company’s inverse rendering tool that turns a set of static images into a realistic 3D scene, has won the Best Paper award at SIGGRAPH 2022 which took place in Vancouver earlier this month.
One of the best uses of Instant NeRF seen so far comes from San Francisco-based creative director Karen X. Cheng and software engineer James Perlman who explored reflections in a mirror in the video below.
“The algorithm itself is groundbreaking — the fact that you can render a physical scene with higher fidelity than normal photogrammetry techniques is just astounding. It’s incredible how accurately you can reconstruct lighting, color differences or other tiny details.”
James Perlman
Karen and James are able to produce about 20 scenes a day using an NVIDIA RTX A6000 GPU to render, train and preview their 3D scenes.
“It even makes mistakes look artistic. We really lean into that, and play with training a scene less sometimes, experimenting with 1,000, or 5,000 or 50,000 iterations. Sometimes I’ll prefer the ones trained less because the edges are softer and you get an oil-painting effect.”
Karen X Cheng
At Dpt. in Montreal, partner and innovation lead Hugues Bruyère is using Instant NeRF daily to manipulate data captured for traditional photogrammetry using mirrorless digital cameras, smartphones, 360 cameras and drones. Using pictures taken with a smartphone, Hugues created an Instant NeRF render of an ancient marble statue of Zeus from an exhibition at Toronto’s Royal Ontario Museum.
“The aspect of capturing itself is being democratized, as camera and software solutions become cheaper. In a few months or years, people will be able to capture objects, places, moments and memories and have them volumetrically rendered in real time, shareable and preserved forever.”
Hugues Bruyère, Dpt.
Spatial computing company EveryPoint’s Jonathan Stephens uses Instant NeRF to create 3D views of industrial and transport locations that clients can explore and experience to help them manage their resources and assets.
“What I really like about Instant NeRF is that you quickly know if your render is working. With a large photogrammetry set, you could be waiting hours or days. Here, I can test out a bunch of different datasets and know within minutes.”
Jonathan Stephens
Jonathan has even experimented with footage shot using lightweight devices like smart glasses.
Source: NVIDIA blog