Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

How lighting works in Simulon Using a professional on-set VFX kit, we showcase our unique Image Based Lighting system. Simulon employs ML to create a 360° HDRI from just one LDR shot, aligning it perfectly with scene data. Our virtual camera replicates the physical camera’s response to light, syncing...

diveshnaidoo's profile picture

Divesh Naidoo

7,960 subscribers

275,172 Aufrufe • vor 3 Jahren •via X (Twitter)

KunstWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Divesh Naidoo
Divesh Naidoovor 3 Jahren

In case you missed it, this is what the final render from this lighting demo looks like. The animation is also timecode synced so you shoot for the action you see in-camera 🎥

Profilbild von Ryan 🦋elborn
Ryan 🦋elbornvor 3 Jahren

@Simulon This is absurd. @Simulon is so dialed in.

Profilbild von SΔM | Δˣ Games.
SΔM | Δˣ Games.vor 3 Jahren

@Simulon So witchcraft, essentially.

Profilbild von CoffeeVectors
CoffeeVectorsvor 3 Jahren

@Simulon Sick! 🔥

Profilbild von Pablo de Rosacruz
Pablo de Rosacruzvor 3 Jahren

@Simulon I wake up everyday dreaming of my waitlist email to access this

Profilbild von DENJIN-K
DENJIN-Kvor 3 Jahren

@Simulon Definitely want to try this tech out 🙌

Profilbild von DonDeBaron
DonDeBaronvor 2 Jahren

@Simulon Didnt want to get a iphone but now i have to😭😭😭please let me know when beta so i can start saving money 🦾🦾🦾

Profilbild von Divesh Naidoo
Divesh Naidoovor 2 Jahren

@Simulon Updates on the product and release this month!

Profilbild von elsa bleda
elsa bledavor 3 Jahren

@Simulon 🔮🐉

Profilbild von Jarryd Muir
Jarryd Muirvor 3 Jahren

@Simulon Cape Town!!! 🫶

Ähnliche Videos

POV: How Simulon works on an iPhone: 1. Create a scene 2. Capture world data 3. Add 3D objects 4. Shoot video 5. Get a photorealistic cloud render Final render at the end. Next up: How Simulon connects to Blender.
1:31

POV: How Simulon works on an iPhone: 1. Create a scene 2. Capture world data 3. Add 3D objects 4. Shoot video 5. Get a photorealistic cloud render Final render at the end. Next up: How Simulon connects to Blender.

Divesh Naidoo

37,114 Aufrufe • vor 2 Jahren

Let me share a long-awaited behind-the-scenes video of how Simulon works. It all starts with setting up a scene. You set the location, lighting conditions and capture the light map with a few turns. After that, you can capture the environment mesh using the Lidar scanner. That's the moment the fun begins. You can bring in your #3D models with animations and capture a video of up to 50" using the #AR preview on screen. After that is done, you send the footage to the cloud and in a couple of minutes you get back an incredible #CGI shot. And this is just the beginning. Follow Gabriele Romagnoli to see how Simulon integrates with #Blender and in a full #VFX workflow. A special thanks to Divesh Naidoo for sharing early access and for building something 🤯
1:18

Let me share a long-awaited behind-the-scenes video of how Simulon works. It all starts with setting up a scene. You set the location, lighting conditions and capture the light map with a few turns. After that, you can capture the environment mesh using the Lidar scanner. That's the moment the fun begins. You can bring in your #3D models with animations and capture a video of up to 50" using the #AR preview on screen. After that is done, you send the footage to the cloud and in a couple of minutes you get back an incredible #CGI shot. And this is just the beginning. Follow Gabriele Romagnoli to see how Simulon integrates with #Blender and in a full #VFX workflow. A special thanks to Divesh Naidoo for sharing early access and for building something 🤯

Gabriele Romagnoli

142,533 Aufrufe • vor 2 Jahren

A few months back, we teased clips from our upcoming VFX app, Simulon. We've since been hard at work making Simulon the most powerful, robust, and intuitive VFX workflow available. This weekend, we'll begin granting access to select creators. Simulon is now able to produce videos that are indistinguishable from reality - can you spot which objects on the table are real and which were added with Simulon? Watch to the end to see if you're right. A thread 🧵
0:36

A few months back, we teased clips from our upcoming VFX app, Simulon. We've since been hard at work making Simulon the most powerful, robust, and intuitive VFX workflow available. This weekend, we'll begin granting access to select creators. Simulon is now able to produce videos that are indistinguishable from reality - can you spot which objects on the table are real and which were added with Simulon? Watch to the end to see if you're right. A thread 🧵

Divesh Naidoo

119,328 Aufrufe • vor 2 Jahren

To showcase Simulon's capability with high-fidelity assets and to highlight the difference between what you see in real-time AR versus the precision of offline cloud rendering, we've made a video using a detailed human scan by 3D Scanstore. Our workflow was designed to closely align the visuals in real-time AR with our offline cloud renders. The video below demonstrates this, transitioning between the AR preview and the final cloud render. This preview lets creators foresee the final VFX shot, reducing guesswork in lighting and composition.
0:31

To showcase Simulon's capability with high-fidelity assets and to highlight the difference between what you see in real-time AR versus the precision of offline cloud rendering, we've made a video using a detailed human scan by 3D Scanstore. Our workflow was designed to closely align the visuals in real-time AR with our offline cloud renders. The video below demonstrates this, transitioning between the AR preview and the final cloud render. This preview lets creators foresee the final VFX shot, reducing guesswork in lighting and composition.

Divesh Naidoo

265,621 Aufrufe • vor 2 Jahren

Lighting is key to creating believable VFX. Simulon generates accurate 360 hdr lighting in seconds. But there’s something much stranger going on in this video. The chrome ball is being moved through the world as if it is actually there. How do you think this is possible? 👀 We’ve built something that will completely change how 3D visual effects are made and it’s coming to Simulon next week.
0:31

Lighting is key to creating believable VFX. Simulon generates accurate 360 hdr lighting in seconds. But there’s something much stranger going on in this video. The chrome ball is being moved through the world as if it is actually there. How do you think this is possible? 👀 We’ve built something that will completely change how 3D visual effects are made and it’s coming to Simulon next week.

Divesh Naidoo

119,328 Aufrufe • vor 10 Monaten

It's wild what you can one-shot with Gemini 3 and Nano Banana Pro in AIS. Here's an app to relight an image: > Use a 3D environment with a bust of a person and a light source, I should be able to move the light source around to cast shadows in different ways, add multiple light sources, etc. Then I should be able to capture the scene, pass it alongside an input image to Nano Banana Pro to change the lighting on an input
0:43

It's wild what you can one-shot with Gemini 3 and Nano Banana Pro in AIS. Here's an app to relight an image: > Use a 3D environment with a bust of a person and a light source, I should be able to move the light source around to cast shadows in different ways, add multiple light sources, etc. Then I should be able to capture the scene, pass it alongside an input image to Nano Banana Pro to change the lighting on an input

fofr

25,907 Aufrufe • vor 8 Monaten

Every single final clip you see in this video was rendered with Ray3 Modify in Dream Machine by Luma. Each clip originating from a handcrafted 3D scene. This is a glimpses of the 3D/VFX workflows of the future, keeping the parts we love and making the whole process more efficient and limitless.
0:43

Every single final clip you see in this video was rendered with Ray3 Modify in Dream Machine by Luma. Each clip originating from a handcrafted 3D scene. This is a glimpses of the 3D/VFX workflows of the future, keeping the parts we love and making the whole process more efficient and limitless.

Luma | Dream Lab

32,071 Aufrufe • vor 7 Monaten

Excited to share a new Simulon workflow video, showcasing real-time environment meshing, multi-surface object placement and persistent AR - allowing you to save & revisit 3D scenes in the real world 🌐✨ Beginning with a cloud-rendered sequence, we then break down the process.
1:38

Excited to share a new Simulon workflow video, showcasing real-time environment meshing, multi-surface object placement and persistent AR - allowing you to save & revisit 3D scenes in the real world 🌐✨ Beginning with a cloud-rendered sequence, we then break down the process.

Divesh Naidoo

57,878 Aufrufe • vor 2 Jahren

I wanted to see how far AI video could actually go when you give it a real cinematic story. So I started with one simple idea: a lone astronaut standing on an unknown planet, watching a massive spacecraft emerge from behind the mountains. Then I built the scene with **Seedance 2.5 on Morphic**. The goal wasn’t just to generate a pretty shot. I wanted the whole sequence to feel like one continuous scene — the same character, the same environment, consistent lighting, realistic ocean reflections, atmospheric movement, and a spacecraft that actually feels massive. What surprised me most was how much control you can get over the storytelling. I could take the scene from a wide cinematic establishing shot → to the astronaut’s reaction → to the spacecraft reveal → and finally into a massive energy portal over the ocean. And the best part? I didn’t need a camera, actors, a film crew, or a huge VFX setup. Just the idea, the prompt, and **Morphic**. This is the kind of AI video workflow that makes you rethink what a solo creator can actually produce. Seedance 2.5 is now available on Morphic What would you create with it? 👀
0:30

I wanted to see how far AI video could actually go when you give it a real cinematic story. So I started with one simple idea: a lone astronaut standing on an unknown planet, watching a massive spacecraft emerge from behind the mountains. Then I built the scene with **Seedance 2.5 on Morphic**. The goal wasn’t just to generate a pretty shot. I wanted the whole sequence to feel like one continuous scene — the same character, the same environment, consistent lighting, realistic ocean reflections, atmospheric movement, and a spacecraft that actually feels massive. What surprised me most was how much control you can get over the storytelling. I could take the scene from a wide cinematic establishing shot → to the astronaut’s reaction → to the spacecraft reveal → and finally into a massive energy portal over the ocean. And the best part? I didn’t need a camera, actors, a film crew, or a huge VFX setup. Just the idea, the prompt, and **Morphic**. This is the kind of AI video workflow that makes you rethink what a solo creator can actually produce. Seedance 2.5 is now available on Morphic What would you create with it? 👀

Scarlett

254,209 Aufrufe • vor 13 Tagen

The suspect in a vehicle pursuit and possibly several auto burglaries is in custody after being located using thermal drone technology. The below video shows the capture, and at the end, you can see the lighting conditions without the thermal tech. More info below
1:17

The suspect in a vehicle pursuit and possibly several auto burglaries is in custody after being located using thermal drone technology. The below video shows the capture, and at the end, you can see the lighting conditions without the thermal tech. More info below

Lawrence Police

70,935 Aufrufe • vor 2 Jahren

Cool footage of 2 bull moose sparring from just 2 weeks ago! And then toward the end of the sequence another small bull decides to join in the fun. All-in-all, some trail camera gold! We’ve only captured this on camera one other time so far. But this footage is much better than our other observation, in part, because the lighting was almost perfect in this video. Suffice it to say, we were pretty excited to capture this footage. In total, the moose were in front of the camera for 14 minutes but we condensed it down to the highlights here. A fair portion of the videos were the bulls just standing there staring at each other.
2:10

Cool footage of 2 bull moose sparring from just 2 weeks ago! And then toward the end of the sequence another small bull decides to join in the fun. All-in-all, some trail camera gold! We’ve only captured this on camera one other time so far. But this footage is much better than our other observation, in part, because the lighting was almost perfect in this video. Suffice it to say, we were pretty excited to capture this footage. In total, the moose were in front of the camera for 14 minutes but we condensed it down to the highlights here. A fair portion of the videos were the bulls just standing there staring at each other.

Voyageurs Wolf Project

10,994 Aufrufe • vor 1 Jahr

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.
0:40

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 Aufrufe • vor 3 Monaten

As part of our walkthrough series, today we are covering labor in the physical AI era—why real robots and real jobs hinge on grounded data, human judgment, and a pipeline from capture to delivery, not simulation alone. If you’re following Harbor or the future of work in AI, this one connects the dots in a few minutes.
5:35

As part of our walkthrough series, today we are covering labor in the physical AI era—why real robots and real jobs hinge on grounded data, human judgment, and a pipeline from capture to delivery, not simulation alone. If you’re following Harbor or the future of work in AI, this one connects the dots in a few minutes.

Harbor ML

13,443 Aufrufe • vor 3 Monaten

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.
0:33

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,567 Aufrufe • vor 3 Jahren

More on this same corner of megalithic wall in Cuzco. There is a section just to the right of the corner blocks, where the stones have separated about an inch, revealing the amazing complex surfaces of both blocks, and how they fit each other perfectly. It is difficult to capture with a camera, but this short video shows it pretty well.
0:34

More on this same corner of megalithic wall in Cuzco. There is a section just to the right of the corner blocks, where the stones have separated about an inch, revealing the amazing complex surfaces of both blocks, and how they fit each other perfectly. It is difficult to capture with a camera, but this short video shows it pretty well.

Brothers of the Serpent Podcast

19,031 Aufrufe • vor 1 Jahr

Cool thing about Simulon is that I can make a quick 3D scan of the environment and use it for occlusions and shadow catching. In addition to capturing scene lighting, this is one of those things that was doable, but was a pain to setup - now you get it right out of the box 😍
0:26

Cool thing about Simulon is that I can make a quick 3D scan of the environment and use it for occlusions and shadow catching. In addition to capturing scene lighting, this is one of those things that was doable, but was a pain to setup - now you get it right out of the box 😍

Bilawal Sidhu

23,162 Aufrufe • vor 2 Jahren

The video that almost got me banned on TikTok for "hate speech." ⚠️ Our institutions are changing, and it is impacting real medical science. From the history of institutional capture to the actual data behind modern healthcare procedures, we need to take a closer look at what is happening in the system. Watch the full video to see how these pieces connect. #InstitutionalCapture #MedicalTruth #ObjectiveScience
6:13

The video that almost got me banned on TikTok for "hate speech." ⚠️ Our institutions are changing, and it is impacting real medical science. From the history of institutional capture to the actual data behind modern healthcare procedures, we need to take a closer look at what is happening in the system. Watch the full video to see how these pieces connect. #InstitutionalCapture #MedicalTruth #ObjectiveScience

Nicole Nathern-Hedrick

17,485 Aufrufe • vor 28 Tagen

Back in the day, Stargate accomplished a lot on what, at the time, was a pretty modest budget. A big part of our success was thanks to our in-house visual effects team led by VFX Supervisor Mark Savela. Check out this EVA chasm jump sequence from Stargate: Atlantis's "Adrift" featuring Sheppard and Zelenka. It was shot in what we coined, appropriately enough, the VFX stage - home to the village set, some Atlantis interiors, and the hive ship.
0:28

Back in the day, Stargate accomplished a lot on what, at the time, was a pretty modest budget. A big part of our success was thanks to our in-house visual effects team led by VFX Supervisor Mark Savela. Check out this EVA chasm jump sequence from Stargate: Atlantis's "Adrift" featuring Sheppard and Zelenka. It was shot in what we coined, appropriately enough, the VFX stage - home to the village set, some Atlantis interiors, and the hive ship.

Joseph Mallozzi 🏴‍☠️

92,275 Aufrufe • vor 7 Monaten