Dennis Gustafsson's banner

Dennis Gustafsson

@voxagonlabs • 84,244 subscribers

Game designer and programmer. Founder of @tuxedolabs. Teardown @teardowngame, Smash Hit, PinOut, Does not Commute, Sprinkle, Granny Smith, Meqon and Dresscode.

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Some physically driven animation for your Wednesday afternoon. After months of trying to get RL to look nice, I've switched over to good old procedural animation.

Some physically driven animation for your Wednesday afternoon. After months of trying to get RL to look nice, I've switched over to good old procedural animation.

Dennis Gustafsson

62,184 次观看 • 2 个月前

The spaghetti stress test. Each batch is about 800 bodies, connected with shape-preserving ball joints.

The spaghetti stress test. Each batch is about 800 bodies, connected with shape-preserving ball joints.

Dennis Gustafsson

255,650 次观看 • 1 年前

Experimenting with an in-game build mode. A lot of people have been requesting that. I can see why :)

Experimenting with an in-game build mode. A lot of people have been requesting that. I can see why :)

Dennis Gustafsson

582,558 次观看 • 3 年前

Joints in the multi-threaded solver. While simpler to implement in theory, multiple violating constraints are much more sensitive to ordering, making them challenging for graph coloring.

Joints in the multi-threaded solver. While simpler to implement in theory, multiple violating constraints are much more sensitive to ordering, making them challenging for graph coloring.

Dennis Gustafsson

107,982 次观看 • 1 年前

It's a strange job, but look at that stability!

It's a strange job, but look at that stability!

Dennis Gustafsson

117,275 次观看 • 1 年前

The new voxel format is finally starting to come together. It uses a brickmap that enables large, sparse objects, unique properties for each voxel (no palette) and really fast scene updates.

The new voxel format is finally starting to come together. It uses a brickmap that enables large, sparse objects, unique properties for each voxel (no palette) and really fast scene updates.

Dennis Gustafsson

118,988 次观看 • 1 年前

Time to put those deformable voxels to work. Here is a very quick softbody test. There are some artefacts and missing motion vectors but there's potential!

Time to put those deformable voxels to work. Here is a very quick softbody test. There are some artefacts and missing motion vectors but there's potential!

Dennis Gustafsson

140,069 次观看 • 2 年前

Colorful deformable voxel sausages with self-collision. If you have no idea what this is useful for, that makes two of us.

Colorful deformable voxel sausages with self-collision. If you have no idea what this is useful for, that makes two of us.

Dennis Gustafsson

135,619 次观看 • 2 年前

Some work-in-progress third person camera action and procedural driving animations.

Some work-in-progress third person camera action and procedural driving animations.

Dennis Gustafsson

145,896 次观看 • 2 年前

I finally got graph coloring working properly in the solver with good performance. Now large piles can be solved on multiple threads in deterministic order. It really helps with stability. Big thanks to Erin Catto pointing me in the right direction!

I finally got graph coloring working properly in the solver with good performance. Now large piles can be solved on multiple threads in deterministic order. It really helps with stability. Big thanks to Erin Catto pointing me in the right direction!

Dennis Gustafsson

78,357 次观看 • 1 年前

I've been trying to implement a parallel rigid body solver. It's a tricky problem in physics to solve a huge pile of objects on multiple threads. I've tried graph coloring and other means of splitting up the problem, but so far a locking primitive per body is the most efficient..

I've been trying to implement a parallel rigid body solver. It's a tricky problem in physics to solve a huge pile of objects on multiple threads. I've tried graph coloring and other means of splitting up the problem, but so far a locking primitive per body is the most efficient..

Dennis Gustafsson

65,477 次观看 • 1 年前

Experimenting with a new way of doing stochastic transparency. It still uses a checkerboard pattern, but allows for both variable transparency, tinted and frosted glass by recombining transparent and opaque pixels in a post-pass. Looks pretty promising so far!

Experimenting with a new way of doing stochastic transparency. It still uses a checkerboard pattern, but allows for both variable transparency, tinted and frosted glass by recombining transparent and opaque pixels in a post-pass. Looks pretty promising so far!

Dennis Gustafsson

112,635 次观看 • 3 年前

I've done some graphics research lately and been tinkering with a new voxel renderer. It's pretty different from the one in Teardown, focusing heavily on GI. There are no explicit light sources in this scene (except for the sun), just emissive voxels.

I've done some graphics research lately and been tinkering with a new voxel renderer. It's pretty different from the one in Teardown, focusing heavily on GI. There are no explicit light sources in this scene (except for the sun), just emissive voxels.

Dennis Gustafsson

75,197 次观看 • 2 年前

It's getting better, but progress is pretty slow. The reward here is for staying upright while matching a rest post. This one has about 65k parameters trained with PPO for half an hour.

It's getting better, but progress is pretty slow. The reward here is for staying upright while matching a rest post. This one has about 65k parameters trained with PPO for half an hour.

Dennis Gustafsson

33,353 次观看 • 1 年前

Baby steps towards physically based animation with reinforcement learning...

Baby steps towards physically based animation with reinforcement learning...

Dennis Gustafsson

32,132 次观看 • 1 年前

Reinforcement learning experiments continues. Still a bit janky, but it is clearly learning something. This is about an hour into training.

Reinforcement learning experiments continues. Still a bit janky, but it is clearly learning something. This is about an hour into training.

Dennis Gustafsson

22,082 次观看 • 9 个月前

没有更多内容可加载