Today at the start of my graduate graphics class we showed a VR metaroom demo with multiple people in the classroom wearing Quest VR headsets, holding controllers and collaborating over WebVR. We made it even more interesting by having the entire scene — the room with all of its furniture and the avatars of all […]
Seeing the future take shape Read More »
For a project during my masters degree, we implemented the paper Learning to Generate Chairs by Dosovitskiy et. al. in PyTorch. The only implementation available was the author’s in Caffe with Lua, so we set off to create a clean open source implementation of the work. This work presents an early differentiable renderer using convolutional
Learning to Generate Chairs with Convolutional Neural Networks Read More »
1.This week I found a paper, SDM-NET: Deep Generative Network for Structured Deformable Mesh. Their main idea is to decompose a 3D object into parts. And each part can be deformed from a homeomorphic simple object. Their network can also learn the support and symmetry information from the input. The part structures and geometries are
Paper reading: SDM-NET & New tools for 3D deep learning Read More »
This week I setup a 15-meter walkway in the lab for the obstacle experiment in walking paradigm. I chose to use Vive pro with a wireless adapter to accomplish a wireless VR experience. Compared with Oculus Quest, the wireless Vive pro is much heavier, and it is still constrained by the coverage of Lighthouses and
Tested a 15m Walkway Read More »
I started an experiment if it’s possible to take a screenshot of a camera that takes a screenshot of what the camera is seeing which then is rendered to a photograph in virtual reality. Although I expected the performance wouldn’t be too well since it’s using the Oculus Quest, but it turned out it worked
Virtual Reality Wildlife Photography Simulator Read More »
This last week or so I’ve been building a parallel world. I measured all of the sizes in a section of our lab — walls, floors, tables, and so forth. Then I built a computer graphic copy of that world, matching the real thing down to the centimeter. I can walk around in my parallel
Over the years, I’ve work on a side project – a C++ OpenGL rendering engine that I use as a staging ground for experiments with procedural generation. One feature I had particularly had fun implementing, was adding heightmap rendering, with a node based graph built ontop of DearImGUI, with a mask painter alongside (the effects
Node Based Terrain Generation Read More »
Last week I finish the function for the pose skeleton normalization. Given a referenced skeleton expressed with global coordinates, we can take some joints of it(instead of all joints) and normalize the length of the chosen joints of the skeletons in other frames. All the computations are using PyTorch’s tensor, which can be easily used
Normalize the pose and visualization Read More »
A few weeks earlier, I talked about two papers I read regarding gait balance when fixed or suddenly appeared obstacles are involved. The papers are Age Effects on Strategies Used to Avoid Obstacles, and Anxiety-mediated gait adaptations reduce errors of obstacle negotiation among younger and older adults: Implications for fall risk. We have been looking for protocols and
Virtual Obstacles in Gait Read More »
Last week, I’ve finally successfully installed Unity ML Agents after several attempts in the past. As a person who has a design & research background, I find it very interesting to test tools that implement machine learning. I hope to learn more about the basics of machine learning which I believe could be complimentary to
Installing Unity ML Agents Read More »
