Loading video...

Video Failed to Load

Go Home

Oldies but goldies: R. Keys, Cubic convolution interpolation for digital image processing, 1980. Introduces bicubic interpolation, the most frequently used image interpolation method.

gabrielpeyre's profile picture

Gabriel Peyré

100,475 subscribers

37,791 views • 1 year ago •via X (Twitter)

Science & TechnologyArtsEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇
0:10

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇

Gradio

93,074 views • 2 years ago

added camera interpolation, looking around has a little more weight to it
0:19

added camera interpolation, looking around has a little more weight to it

dollo

37,184 views • 1 year ago

🧍‍♀️' " 'Fara - Idle Animation [WIP.02]' " '🧍‍♀️ - Proper approach to animation: animating in Linear Interpolation first, before adding Constant Interpolation - New Color: Healing, referencing that capoeira lady from that fighting game (I don't wanna get sued)
0:18

🧍‍♀️' " 'Fara - Idle Animation [WIP.02]' " '🧍‍♀️ - Proper approach to animation: animating in Linear Interpolation first, before adding Constant Interpolation - New Color: Healing, referencing that capoeira lady from that fighting game (I don't wanna get sued)

RemyHobo 🙌

231,211 views • 1 year ago

Found out there's a build of SRB2 that allows for more frames in model animations. Way better than interpolation!
0:18

Found out there's a build of SRB2 that allows for more frames in model animations. Way better than interpolation!

Logan's Sonic Zone

17,291 views • 2 years ago

The Stable Video Diffusion model just dropped 🔥 The new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:
0:10

The Stable Video Diffusion model just dropped 🔥 The new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:

Dreaming Tulpa 🥓👑

457,724 views • 2 years ago

Oldies but goldies: B Poljak, Some methods of speeding up the convergence of iteration methods, 1964. Introduces momentum methods to speed up gradient descent schemes.
0:10

Oldies but goldies: B Poljak, Some methods of speeding up the convergence of iteration methods, 1964. Introduces momentum methods to speed up gradient descent schemes.

Gabriel Peyré

27,859 views • 1 year ago

A suite of new improvements have been released for the Camera and Navigation functions in #Roblox Studio. These improvements include camera speed customizability, focus interpolation, logarithmic zoom, and more...
0:16

A suite of new improvements have been released for the Camera and Navigation functions in #Roblox Studio. These improvements include camera speed customizability, focus interpolation, logarithmic zoom, and more...

Bloxy News

74,721 views • 2 years ago

transition between orthographic and perspective with linear matrix interpolation🙌🥹🌠 (no idea what to do with that of course) #gamedev #indiegame #indiegamedev
0:10

transition between orthographic and perspective with linear matrix interpolation🙌🥹🌠 (no idea what to do with that of course) #gamedev #indiegame #indiegamedev

Boot Danubien✨

20,093 views • 1 year ago

Oldies but goldies: Y Nesterov, A method for solving a convex programming problem with convergence rate O(1/k^2). Improves the 1/k rate of vanilla gradient descent to 1/k^2.
0:10

Oldies but goldies: Y Nesterov, A method for solving a convex programming problem with convergence rate O(1/k^2). Improves the 1/k rate of vanilla gradient descent to 1/k^2.

Gabriel Peyré

47,616 views • 1 year ago

The linear interpolation of the camera in Forces to Shadow Gens really bugs me. This small change would honestly do a lot to improve the feel of recent Sonic games, IMO.
0:18

The linear interpolation of the camera in Forces to Shadow Gens really bugs me. This small change would honestly do a lot to improve the feel of recent Sonic games, IMO.

Omni Jacala

42,097 views • 1 year ago

New: @𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛/𝚍𝚒𝚛𝚎𝚌𝚝𝚒𝚟𝚎𝚜 Ready-made directives for Generative UI → $format - currencies, dates, percentages via Intl → $t - i18n with key interpolation → $math - arithmetic at render time → $pluralize, $concat, $join, $count Import the ones you need
0:14

New: @𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛/𝚍𝚒𝚛𝚎𝚌𝚝𝚒𝚟𝚎𝚜 Ready-made directives for Generative UI → $format - currencies, dates, percentages via Intl → $t - i18n with key interpolation → $math - arithmetic at render time → $pluralize, $concat, $join, $count Import the ones you need

Chris Tate

58,060 views • 2 months ago

My latest computer vision project - Tennis🎾 Featuring: -Player, ball, racquet detection -Player poses -Exclusion zones to kill false positives -Interpolation and smoothing for clean ball trails All running at over 30FPS!
0:16

My latest computer vision project - Tennis🎾 Featuring: -Player, ball, racquet detection -Player poses -Exclusion zones to kill false positives -Interpolation and smoothing for clean ball trails All running at over 30FPS!

mirrash.eth 🦇🔊

487,201 views • 3 months ago

3. Modify image Use this prompt to modify the image you have chosen: "Modify image [1] with seed [1470033597]: add a parrot on her shoulder" Dall-E 3 identifies the image and makes the changes for you! Tips and tricks: - You can generate as many variations as you like. - It's also possible to remove an element from the image using the same method. - Sometimes the image isn't 100% identical, but still looks very similar.
0:10

3. Modify image Use this prompt to modify the image you have chosen: "Modify image [1] with seed [1470033597]: add a parrot on her shoulder" Dall-E 3 identifies the image and makes the changes for you! Tips and tricks: - You can generate as many variations as you like. - It's also possible to remove an element from the image using the same method. - Sometimes the image isn't 100% identical, but still looks very similar.

Paul Couvert

44,072 views • 2 years ago

Basic seamless loop of a scrolling scene: Create a source tile. Instance it on two adjacent empties. Animate the empties along x or y one "unit" with linear interpolation. Finally, place your subject in the middle. #b3d
0:13

Basic seamless loop of a scrolling scene: Create a source tile. Instance it on two adjacent empties. Animate the empties along x or y one "unit" with linear interpolation. Finally, place your subject in the middle. #b3d

Aaron

35,013 views • 2 years ago

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)
0:17

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

Ricardo Martin-Brualla

21,685 views • 1 year ago

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥
0:14

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥

Linoy Tsaban

14,426 views • 1 year ago

Interactive article: How to animate multiplayer cursors. Rendering smooth cursors always needs interpolation, as network conditions are never perfect—here's how to do it. I wrote this a few years back, techniques still apply! Link ↓
0:14

Interactive article: How to animate multiplayer cursors. Rendering smooth cursors always needs interpolation, as network conditions are never perfect—here's how to do it. I wrote this a few years back, techniques still apply! Link ↓

Chris Nicholas

101,759 views • 5 months ago

Another highly requested feature (drag and drop image processing)
0:15

Another highly requested feature (drag and drop image processing)

Theo - t3.gg

72,385 views • 1 year ago

The most painful image for the Cambodian people💔 PRAY FOR CAMBODIA #CambodiaNeedPeace
0:17

The most painful image for the Cambodian people💔 PRAY FOR CAMBODIA #CambodiaNeedPeace

Jing

59,316 views • 7 months ago

That 2-pixel selection perspective trick is a lifesaver! But if you need to build an entire city or asset pack with it, doing it manually takes forever. I built PixZels to automate this -it usesmathematical interpolation to instantly project orthogonal views into clean isometric pixel art.
0:11

That 2-pixel selection perspective trick is a lifesaver! But if you need to build an entire city or asset pack with it, doing it manually takes forever. I built PixZels to automate this -it usesmathematical interpolation to instantly project orthogonal views into clean isometric pixel art.

pixel_salvaje

377,590 views • 3 days ago