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

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: #TheAIHardwarePartnershow more

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 #parallaxocclusionshow more

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.show more

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!show more

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 🔥show more

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.show more

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/homeshow more

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

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 BigMediumSmallshow more

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.show more

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.show more

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:show more

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.show more

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.show more

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!show more

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

One more big hit clip from the weekend. This... is the Wayer hit on Kavanagh in real time and in replay. No flag thrown here.show more

You can use the Motion tools in Unreal 5.6... to easily reveal an entire Archviz scene with hundreds of objects, including buildings & foliage. It's super snappy & all real-time. Tutorials have been added to Unreal Motion 5.6show more

He is scared to death. He knows now that... the FBI was always legit and Trump is fxcking with real peoples lives and stuff. He knows this story ends only one way in all the movies… especially the ones based on real life.show more