Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

One more turn with this #AR: added underwater transition. All real-time, based on #ML scene depth estimation. Built in Effect House.

Enuriru's profile picture

Denis Rossiev ᯅ/acc

14,800 subscribers

23,567 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie#AR#ML
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Gave a robot 3D vision with just a regular camera👁️ Full Tutorial: Deployed #Depth Anything V3​ on NVIDIA Robotics Jetson AGX Orin. It estimates depth from 2D images in real-time—no special sensors needed. Just need #Monocular depth estimation + #TensorRT​ optimization + #ROS2​ integration. 👉 Learn more about reComputer Robotics J5011: #TheAIHardwarePartner
0:18

Gave a robot 3D vision with just a regular camera👁️ Full Tutorial: Deployed #Depth Anything V3​ on NVIDIA Robotics Jetson AGX Orin. It estimates depth from 2D images in real-time—no special sensors needed. Just need #Monocular depth estimation + #TensorRT​ optimization + #ROS2​ integration. 👉 Learn more about reComputer Robotics J5011: #TheAIHardwarePartner

Seeed Studio

16,966 Aufrufe • vor 6 Monaten

Create a unique-looking depth effect without adding any geometry to your scene in one click with Parallax It! add-on for Blender 🔶. Get it here: #b3d #blender #blender3d #blendercommunity #parallaxocclusion
0:11

Create a unique-looking depth effect without adding any geometry to your scene in one click with Parallax It! add-on for Blender 🔶. Get it here: #b3d #blender #blender3d #blendercommunity #parallaxocclusion

80 LEVEL

48,553 Aufrufe • vor 2 Jahren

Nano is a depth-aware atmospheric haze plugin that uses ML depth estimation to add physically accurate fog and light scattering to your footage. Works *best* on log footage with visible light sources - it analyzes scene highlights then creates airlight (atmospheric scatter) and halation (light bloom) that responds to actual depth in the scene. Pretty clever approach to getting that cinematic haze look without having to pump a fog machine on set. Makes the OG Trapcode Shine look extremely dated (basically 2D light streaks masked by luminance values), and is yet way more controllable than the current crop of generative AI video-to-video tools.
0:18

Nano is a depth-aware atmospheric haze plugin that uses ML depth estimation to add physically accurate fog and light scattering to your footage. Works *best* on log footage with visible light sources - it analyzes scene highlights then creates airlight (atmospheric scatter) and halation (light bloom) that responds to actual depth in the scene. Pretty clever approach to getting that cinematic haze look without having to pump a fog machine on set. Makes the OG Trapcode Shine look extremely dated (basically 2D light streaks masked by luminance values), and is yet way more controllable than the current crop of generative AI video-to-video tools.

Bilawal Sidhu

275,436 Aufrufe • vor 1 Jahr

The classic SMT turn-based combat system returns with a few twists. ⚔️ Optimize your battles with newly-added demon “Unique Skills,” additional Magatsuhi moves, and more in Shin Megami Tensei V: Vengeance!
0:19

The classic SMT turn-based combat system returns with a few twists. ⚔️ Optimize your battles with newly-added demon “Unique Skills,” additional Magatsuhi moves, and more in Shin Megami Tensei V: Vengeance!

Official ATLUS West

173,206 Aufrufe • vor 2 Jahren

Consistency is what makes this feel real. One character, multiple professions, seamless scene changes, all in a single take. Created with Gemini Omni Flash on Pollo AI 🔥
0:10

Consistency is what makes this feel real. One character, multiple professions, seamless scene changes, all in a single take. Created with Gemini Omni Flash on Pollo AI 🔥

Ai Girllie

42,840 Aufrufe • vor 1 Monat

Testing out audio reactivity and vibecodable shader modules in Sentinel. Describe an effect, Claude builds the node and tests it via mcp. Stack it with real-time SDXL and you get this! More on how this works below.
0:16

Testing out audio reactivity and vibecodable shader modules in Sentinel. Describe an effect, Claude builds the node and tests it via mcp. Stack it with real-time SDXL and you get this! More on how this works below.

Spencer Sterling

12,059 Aufrufe • vor 4 Monaten

Marine traffic. Awesome that people build maps like this showing real-time ship movements all over the world, with in-depth ship and route information. www.marinetraffic .com/en/ais/home
0:12

Marine traffic. Awesome that people build maps like this showing real-time ship movements all over the world, with in-depth ship and route information. www.marinetraffic .com/en/ais/home

Leon

17,043 Aufrufe • vor 1 Jahr

and put more respect on his name cause he built this house y’all are living in now
0:11

and put more respect on his name cause he built this house y’all are living in now

ִ

19,974 Aufrufe • vor 3 Monaten

In the new version of Simulon, we've built a simulated depth of field effect that seamlessly blends CG and real-world elements, mimicking the behavior of a real camera lens. We just love creating miniature shots with shallow focus! Assets by our friends at BigMediumSmall
0:18

In the new version of Simulon, we've built a simulated depth of field effect that seamlessly blends CG and real-world elements, mimicking the behavior of a real camera lens. We just love creating miniature shots with shallow focus! Assets by our friends at BigMediumSmall

Divesh Naidoo

59,080 Aufrufe • vor 1 Jahr

We’ve been spending way too much time on this sidebar with Paul Faivret . We re-structured the Interfere navigation, so we added this subtle animation to transition between the two layers.
0:10

We’ve been spending way too much time on this sidebar with Paul Faivret . We re-structured the Interfere navigation, so we added this subtle animation to transition between the two layers.

Jakub Krehel

71,169 Aufrufe • vor 3 Monaten

I think we just built the most insane 3D VFX workflow. Precision reality editing with Simulon + Blender. • Scan the real world in seconds • Edit in Blender • Sync + reopen in Simulon • View & shoot in real-time AR • Photoreal cloud render in minutes Will share a BTS of this clip shortly.
0:17

I think we just built the most insane 3D VFX workflow. Precision reality editing with Simulon + Blender. • Scan the real world in seconds • Edit in Blender • Sync + reopen in Simulon • View & shoot in real-time AR • Photoreal cloud render in minutes Will share a BTS of this clip shortly.

Divesh Naidoo

38,073 Aufrufe • vor 9 Monaten

6 more followers away from 300. The Kickstarter launches August 31st! 🎉 Our indie game is a turn-based JRPG with mech combat, set in a world built on a lie. Link to our campaign below! 🔽
0:17

6 more followers away from 300. The Kickstarter launches August 31st! 🎉 Our indie game is a turn-based JRPG with mech combat, set in a world built on a lie. Link to our campaign below! 🔽

Lie of Caelum: Spirit - Follow our Kickstarter!

28,109 Aufrufe • vor 12 Tagen

REALLY cool effect for creating lyric videos super fast with AI: 1. made a quick demo track with ElevenLabs 2. nano banana workflow that generates the "cut out ransom style" text based on the lyrics 3. used my transition agent to morph between them Voilà, all in 5 min:
0:13

REALLY cool effect for creating lyric videos super fast with AI: 1. made a quick demo track with ElevenLabs 2. nano banana workflow that generates the "cut out ransom style" text based on the lyrics 3. used my transition agent to morph between them Voilà, all in 5 min:

fabian

16,875 Aufrufe • vor 11 Monaten

This is insane.. in traditional filmmaking, creating a bullet-time effect like this takes hundreds of cameras and days of editing but with 3DGS AI, all you need is ONE image.
0:10

This is insane.. in traditional filmmaking, creating a bullet-time effect like this takes hundreds of cameras and days of editing but with 3DGS AI, all you need is ONE image.

el.cine

97,312 Aufrufe • vor 1 Jahr

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.
0:13

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

MrNeRF

27,428 Aufrufe • vor 1 Jahr

Perplexity Sports! Starting with NFL widgets (built in house) where you can get in depth game summaries, stats and comparisons across players and teams! NBA, EPL, La Liga, champions league, tennis, cricket, etc will all be coming soon!
0:12

Perplexity Sports! Starting with NFL widgets (built in house) where you can get in depth game summaries, stats and comparisons across players and teams! NBA, EPL, La Liga, champions league, tennis, cricket, etc will all be coming soon!

Aravind Srinivas

183,887 Aufrufe • vor 1 Jahr

Introducing Aggregated Order Book Heatmaps For the first time, see liquidity across ALL exchanges in one chart in real-time. No more juggling tabs.
0:16

Introducing Aggregated Order Book Heatmaps For the first time, see liquidity across ALL exchanges in one chart in real-time. No more juggling tabs.

Kiyotaka

66,329 Aufrufe • vor 1 Jahr