Simulation from Two Minute Papers.

Scientific simulation has multiple objectives that allow us a correct and broader perception of the object of study.

Here is an interesting video about complex 3D simulations.

AI video editing from Two Minute Papers.

The correctness of digital data can be questioned, but its alignment with user preferences and actual accuracy will always be an issue.

You can see also on example on this colab notebook.

How artificial intelligence distorts perception from Two Minute Papers.

Like any information by completing, omitting or modifying it, they can distort the perception of the recipient.

A fairly complete video on how to manipulate visual data with artificial intelligence.

Here is a video as complete as possible with examples of how artificial intelligence can distort the perception of what the user sees.

Google’s New AI from Two Minute Papers.

The title for this video is: "Google’s New AI: This is Where Selfies Go Hyper!"

Finnaly C-IPC and more from Two Minute Papers.

Lately I've been looking to post something new in the field of graphics and games. You don't even have to look too hard, because now you can see a result of the new achievements. Here is a video that outperforms them all.

See this document on this webpage.

Simulating A Virtual World from Two Minute Papers.

This is a simulation of a virtual word build with The paper "Synthetic Silviculture: Multi-scale Modeling of Plant Ecosystems" is available here:

Another new AI from Two Minute Papers.

Approximate Differentiable One-Pixel Point Rendering is a new differentiable neural rendering pipeline for scene refinement and novel view synthesis see the official page and the video from Two Minute Papers.

Image Super-Resolution via Iterative Refinement from Two Minute Papers.

This is a unoffical implementation about Image Super-Resolution via Iterative Refinement(SR3) by Pytorch.

There are some implement details with paper description, which maybe different with actual SR3 structure due to details missing.

We used the ResNet block and channel concatenation style like vanilla DDPM.

We used the attention mechanism in low resolution feature(16×16) like vanilla DDPM.

We encoding the $\gamma$ as FilM strcutrue did in WaveGrad, and embedding it without affine transformation.

Read more on the GitHub project.

Elastic Simulations from Two Minute Papers.

... other simulations from Two Minute Papers.

This youtube channel comes with old and news and pieces of information about graphics.

Ships, Splashes, and Waves on a Vast Ocean from Two Minute Papers.

The simulation of large open water surface is challenging using a uniform volumetric discretization of the Navier-Stokes equations. Simulating water splashes near moving objects, which height field methods for water waves cannot capture, necessitates high resolutions. Such simulations can be carried out using the Fluid-Implicit-Particle (FLIP) method. However, the FLIP method is not efficient for the long-lasting water waves that propagate to long distances, which require sufficient depth for a correct dispersion relationship. This paper presents a new method to tackle this dilemma through an efficient hybridization of volumetric and surface-based advection-projection discretizations. We design a hybrid time-stepping algorithm that combines a FLIP domain and an adaptively remeshed Boundary Element Method (BEM) domain for the incompressible Euler equations. The resulting framework captures the detailed water splashes near moving objects with the FLIP method, and produces convincing water waves with correct dispersion relationships at modest additional costs.

Martial arts from Two Minute Papers.

The paper "Neural Animation Layering for Synthesizing Martial Arts Movements" is available here.

Virtual Bones with Direct Delta Mush .

Direct Delta Mush (DDM) is a high-quality, direct skinning method with a low setup cost. However, its storage and run-time computing cost are relatively high for two reasons: its skinning weights are 4 × 4 matrices instead of scalars like other direct skinning methods, and its computation requires one 3 × 3 Singular Value Decomposition per vertex. see this PDF.

see this video for SIGGRAPH 2021 Presentation: Direct Delta Mush Skinning Compression with Continuous Examples

AI-Based from Two Minute Papers.

An example of effects created using artificial intelligence from Two Minute Papers.