Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Let me share how the maps look like. Normal was estimated from the source image with StableNormal ( and Refined Depth came from promptDA ( + Lidar Depth. If you pause the video, you will see the differences in depths.

ChrisAtKIRI's profile picture

Chris make some 3D scans

1,621 subscribers

44,280 Aufrufe • vor 1 Jahr •via X (Twitter)

GamingWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Doesn't look like the super low-res depth maps from the iPhone Pro's LiDAR sensor would be too useful as supervision (or sanity check) for recent monocular depth estimators.
0:13

Doesn't look like the super low-res depth maps from the iPhone Pro's LiDAR sensor would be too useful as supervision (or sanity check) for recent monocular depth estimators.

Chris Offner

66,068 Aufrufe • vor 1 Jahr

Some updates on the multiview vistadream pipeline with Rerun! Rerun came in extremely useful here, as being able to visualize depths at each stage of the pipeline allowed me to debug some nasty bugs. Since the last time, I was only working with a single image input. I've added in VGGT as my multiview pose + depth estimator. It works REALLY well for getting camera poses, but the depths are not that great. To try and fix that, I estimated depth maps from MoGeV2 for each of the views, and scale+shift aligned them so that they would match up to the confident sections of VGGT's depth predictions. You can see in the video just how much sharper the visualized 2d depth maps are! The biggest issue continues to be the multiview consistency 🫠 That's up next, along with actually training the Gaussian splat. Lots of work went into actually understanding inputs+outputs for VGGT. I had some funky bugs where the confidence values would all collapse to true I'm also really excited for this pipeline to use Difix3D+ Nvidia instead of Flux Inpainting, it seems like a better suited for a multiview pipeline.
0:14

Some updates on the multiview vistadream pipeline with Rerun! Rerun came in extremely useful here, as being able to visualize depths at each stage of the pipeline allowed me to debug some nasty bugs. Since the last time, I was only working with a single image input. I've added in VGGT as my multiview pose + depth estimator. It works REALLY well for getting camera poses, but the depths are not that great. To try and fix that, I estimated depth maps from MoGeV2 for each of the views, and scale+shift aligned them so that they would match up to the confident sections of VGGT's depth predictions. You can see in the video just how much sharper the visualized 2d depth maps are! The biggest issue continues to be the multiview consistency 🫠 That's up next, along with actually training the Gaussian splat. Lots of work went into actually understanding inputs+outputs for VGGT. I had some funky bugs where the confidence values would all collapse to true I'm also really excited for this pipeline to use Difix3D+ Nvidia instead of Flux Inpainting, it seems like a better suited for a multiview pipeline.

Pablo Vela

29,904 Aufrufe • vor 1 Jahr

This is how a river depth is measured using an aircraft and a laser beam. The bathymetric LiDAR can measure depths upto 40m with a accuracy of about 15 cm
0:14

This is how a river depth is measured using an aircraft and a laser beam. The bathymetric LiDAR can measure depths upto 40m with a accuracy of about 15 cm

HOW THINGS WORK

553,964 Aufrufe • vor 2 Jahren

After extracting the depth video, the effect obtained by video referencing is very good. 1. Prepare the reference video 2. Extract the depth video 3. Prepare the character reference images 4. Input the extracted depth video and character reference images into seedance2, and you will get perfect results Complete workflow is below:
0:14

After extracting the depth video, the effect obtained by video referencing is very good. 1. Prepare the reference video 2. Extract the depth video 3. Prepare the character reference images 4. Input the extracted depth video and character reference images into seedance2, and you will get perfect results Complete workflow is below:

SJinn Agent

91,230 Aufrufe • vor 1 Monat

New fal workflow: video restyling with Video Depth Anything and Seedance 2.0 - Restyle the first frame into your target look - Extract consistent depth across the source video - Use that depth to guide Seedance 2.0 through the full sequence - Preserve the original motion and composition while transforming the visual style A simple workflow for turning existing footage into stylized video.
0:16

New fal workflow: video restyling with Video Depth Anything and Seedance 2.0 - Restyle the first frame into your target look - Extract consistent depth across the source video - Use that depth to guide Seedance 2.0 through the full sequence - Preserve the original motion and composition while transforming the visual style A simple workflow for turning existing footage into stylized video.

fal

10,909 Aufrufe • vor 1 Monat

🫡🥰This man will make you understand how and the depth of this mission! #Ringo_Was_Here
0:15

🫡🥰This man will make you understand how and the depth of this mission! #Ringo_Was_Here

Jasper Truth 🇺🇸 🇨🇦

14,822 Aufrufe • vor 22 Tagen

If you followed me from the tiktok- dm me to see the actual video 🍋
0:10

Sensitive content

If you followed me from the tiktok- dm me to see the actual video 🍋

𝙲𝚑𝚎𝚢♡

193,911 Aufrufe • vor 1 Jahr

名画を立体的に鑑賞する方法 Nano Banana Pro (深度/法線マップ生成)→ WebGL(Three.js) スマホでも体験できます👉 【プロンプト】 （法線マップ用） Generate a surface normal map from the input artwork image. Output one RGB image where each pixel encodes the surface normal direction in standard tangent-space format: •R = X direction •G = Y direction •B = Z direction Requirements: •Maintain the same resolution and aspect ratio as the input image. •Normal directions must follow the local geometry implied by brush strokes, shading, and contours. •Do NOT add new artistic elements or repaint the scene. •Only infer plausible micro-geometry and surface orientation. •Ensure smooth, consistent normal transitions without noise. （深度マップ用） Generate a depth map from the input artwork image. Output a single grayscale depth map where: •White = near to the viewer •Black = far from the viewer Requirements: •Maintain the same resolution and aspect ratio as the input image. •Depth must be smooth, continuous, and physically plausible. •Infer only geometric depth that could reasonably exist in the original artwork. •Do NOT add new objects or details. •Do NOT stylize, repaint, or reinterpret the scene. •Avoid texture noise; focus solely on depth structure.
0:11

名画を立体的に鑑賞する方法 Nano Banana Pro (深度/法線マップ生成)→ WebGL(Three.js) スマホでも体験できます👉 【プロンプト】 （法線マップ用） Generate a surface normal map from the input artwork image. Output one RGB image where each pixel encodes the surface normal direction in standard tangent-space format: •R = X direction •G = Y direction •B = Z direction Requirements: •Maintain the same resolution and aspect ratio as the input image. •Normal directions must follow the local geometry implied by brush strokes, shading, and contours. •Do NOT add new artistic elements or repaint the scene. •Only infer plausible micro-geometry and surface orientation. •Ensure smooth, consistent normal transitions without noise. （深度マップ用） Generate a depth map from the input artwork image. Output a single grayscale depth map where: •White = near to the viewer •Black = far from the viewer Requirements: •Maintain the same resolution and aspect ratio as the input image. •Depth must be smooth, continuous, and physically plausible. •Infer only geometric depth that could reasonably exist in the original artwork. •Do NOT add new objects or details. •Do NOT stylize, repaint, or reinterpret the scene. •Avoid texture noise; focus solely on depth structure.

ハシモトタクマ / FunTech

27,192 Aufrufe • vor 8 Monaten

If you ask me how this looks from the top during the stream, you will be banned.
0:11

If you ask me how this looks from the top during the stream, you will be banned.

geodraws

73,663 Aufrufe • vor 8 Monaten

if you see this — you made it through the first week of 2026 all the good that happened from the 1st - today, this candle will now amplify and snowball if you choose to claim it and the snowball will grow as the year unfolds tell the flame what you want most of all by the end of this year, go as in depth as you need— let it consume it and transmute it like snow upon your head as a halo, blessings are about to trickle down and build upon one another just for you to claim — comment SNOW OR a snow emoji or gif ❄️
0:10

if you see this — you made it through the first week of 2026 all the good that happened from the 1st - today, this candle will now amplify and snowball if you choose to claim it and the snowball will grow as the year unfolds tell the flame what you want most of all by the end of this year, go as in depth as you need— let it consume it and transmute it like snow upon your head as a halo, blessings are about to trickle down and build upon one another just for you to claim — comment SNOW OR a snow emoji or gif ❄️

✰FireWitch✰

14,637 Aufrufe • vor 7 Monaten

How to prompt with Grok imagine : You have at least, two complementary ways of learning. 1. You look at an image you like, you click on it, and you see the prompt. This way, you can understand how to create an image you like. 2. You know what image you want to achieve, so you write the prompt yourself. Describe what you want in simple terms. Be clear and concise.
0:18

How to prompt with Grok imagine : You have at least, two complementary ways of learning. 1. You look at an image you like, you click on it, and you see the prompt. This way, you can understand how to create an image you like. 2. You know what image you want to achieve, so you write the prompt yourself. Describe what you want in simple terms. Be clear and concise.

Déborah

1,017,979 Aufrufe • vor 1 Jahr

Check out the velo & the depth on the cutter from Jake Pilarski. If you haven't ever heard of him, join the club, he's been in Indy ball for the last couple of years. Jake Pilarski struck out the side and his last of the inning was 101 MPH. Wow! Can't wait to see more! #dodgers
0:13

Check out the velo & the depth on the cutter from Jake Pilarski. If you haven't ever heard of him, join the club, he's been in Indy ball for the last couple of years. Jake Pilarski struck out the side and his last of the inning was 101 MPH. Wow! Can't wait to see more! #dodgers

Dodgers Daily

37,060 Aufrufe • vor 3 Jahren

1/ today, with the launch of muse image and the preview of muse video, we wanted to share more samples from the model alongside research details and eval results see some more samples from muse video below (and see thread for research blog!)
0:10

1/ today, with the launch of muse image and the preview of muse video, we wanted to share more samples from the model alongside research details and eval results see some more samples from muse video below (and see thread for research blog!)

Alexandr Wang

376,626 Aufrufe • vor 1 Monat

🔥 AI video creation is finally evolving beyond basic motion prompts. Try out Depth Map Control right here: Historically, the hardest part of the process has been maintaining scene consistency: • camera movement • object placement • spatial relationships Thanks to PixVerse Depth Map Control, you can now grab depth data from a reference video and merge it with a fresh image to explore highly directed video generation. The final outcome? Much smoother camera tracking. Highly cohesive visual scenes. It is a powerful workflow that hands creators actual authority over how their AI visuals shift and flow over time. 🎬
0:10

🔥 AI video creation is finally evolving beyond basic motion prompts. Try out Depth Map Control right here: Historically, the hardest part of the process has been maintaining scene consistency: • camera movement • object placement • spatial relationships Thanks to PixVerse Depth Map Control, you can now grab depth data from a reference video and merge it with a fresh image to explore highly directed video generation. The final outcome? Much smoother camera tracking. Highly cohesive visual scenes. It is a powerful workflow that hands creators actual authority over how their AI visuals shift and flow over time. 🎬

Elara Quinn

12,202 Aufrufe • vor 24 Tagen

Ever tried training a splat from depth maps? I have, so you don’t have to. Despite my eager optimism, the results were a flop. It turned out to be a complete waste of time. Hopefully, this spares you the effort!
0:14

Ever tried training a splat from depth maps? I have, so you don’t have to. Despite my eager optimism, the results were a flop. It turned out to be a complete waste of time. Hopefully, this spares you the effort!

MrNeRF

20,549 Aufrufe • vor 1 Jahr