正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Google just revealed an ABSOLUTE depth estimation model 🤯 As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️

Alex Carlier

8,569 subscribers

199,552 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

PatchFusion was just released. Compared to ZoeDepth, it predicts depth maps with much finer details, just look at the comparison below! 🤯 Its main contribution is a new Global-to-Local module and Consistency-Aware Training. More examples below (with code) ⬇️⬇️

PatchFusion was just released. Compared to ZoeDepth, it predicts depth maps with much finer details, just look at the comparison below! 🤯 Its main contribution is a new Global-to-Local module and Consistency-Aware Training. More examples below (with code) ⬇️⬇️

Alex Carlier

92,067 次观看 • 2 年前

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.

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 次观看 • 1 年前

Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵

Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵

Anton Obukhov

49,855 次观看 • 1 年前

A close-up only works when depth feels real. In this shot, we pushed blur and shading to shape the depth of field (DoF), not just for realism, but to deepen the emotion within the frame. Produced by Otsu Labs & Studio Munbou

A close-up only works when depth feels real. In this shot, we pushed blur and shading to shape the depth of field (DoF), not just for realism, but to deepen the emotion within the frame. Produced by Otsu Labs & Studio Munbou

Otsu Labs

33,374 次观看 • 7 个月前

🤯 I didn’t expect Depth to track rooftop parkour this cleanly! Used a fast climbing clip as the motion reference, then swapped in a student with twin tails and a backpack on a coastal school rooftop. The running path, wall contact, jumps, landings, and full-body continuity all hold together surprisingly well. 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. Depth opens up a lot more possibilities for parkour, climbing, martial arts, dance, and other complex full-body motion. Workflow + Prompt below 👇

🤯 I didn’t expect Depth to track rooftop parkour this cleanly! Used a fast climbing clip as the motion reference, then swapped in a student with twin tails and a backpack on a coastal school rooftop. The running path, wall contact, jumps, landings, and full-body continuity all hold together surprisingly well. 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. Depth opens up a lot more possibilities for parkour, climbing, martial arts, dance, and other complex full-body motion. Workflow + Prompt below 👇

Larus Canus

14,384 次观看 • 14 天前

It's also important to verify the token To safeguard against scams, rug pulls, and honeypots, it’s essential to confirm the token's contract Just enter the contract address to access in-depth details about the token’s security:

It's also important to verify the token To safeguard against scams, rug pulls, and honeypots, it’s essential to confirm the token's contract Just enter the contract address to access in-depth details about the token’s security:

Leshka.eth ⛩

19,996 次观看 • 1 年前

🤯 Depth videos perfectly solve false flags on reference videos — and can perfectly recreate both martial arts and dance! Turned a Guan Dao martial arts clip into a Depth motion reference, swapped the fighter for a market auntie, and moved the scene to a T-junction inside a local market 🤣 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. This goes way beyond trending dances. Martial arts, polearms, and other complex movements can all be transferred cleanly with Depth! Workflow + Prompt below 👇

🤯 Depth videos perfectly solve false flags on reference videos — and can perfectly recreate both martial arts and dance! Turned a Guan Dao martial arts clip into a Depth motion reference, swapped the fighter for a market auntie, and moved the scene to a T-junction inside a local market 🤣 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. This goes way beyond trending dances. Martial arts, polearms, and other complex movements can all be transferred cleanly with Depth! Workflow + Prompt below 👇

Larus Canus

49,744 次观看 • 18 天前

Scientists at University of Western Australia set new record for deepest fish ever filmed at a depth of 8,336 meters. During an expedition that took place in August 2022, the research vessel DSSV Pressure Drop embarked on a two-month journey to investigate trenches in the Pacific Ocean near Japan. The primary objective of the expedition was to examine the populations of deep-sea fish. While conducting filming activities, the research team unexpectedly encountered a previously unknown species of snailfish at an astounding depth of 8,336 meters, equivalent to over 27,000 feet, specifically in the Izu-Ogasawara Trench. At a depth of 8,022 meters, scientists successfully obtained two fish from traps. This achievement is noteworthy because it includes the capture of a snailfish species known as Pseudoliparis belyaevi. Notably, this is the first time a fish has been collected from depths exceeding 8,000 meters, as these snailfish were previously observed solely at a shallower depth of 7,703 meters.

Scientists at University of Western Australia set new record for deepest fish ever filmed at a depth of 8,336 meters. During an expedition that took place in August 2022, the research vessel DSSV Pressure Drop embarked on a two-month journey to investigate trenches in the Pacific Ocean near Japan. The primary objective of the expedition was to examine the populations of deep-sea fish. While conducting filming activities, the research team unexpectedly encountered a previously unknown species of snailfish at an astounding depth of 8,336 meters, equivalent to over 27,000 feet, specifically in the Izu-Ogasawara Trench. At a depth of 8,022 meters, scientists successfully obtained two fish from traps. This achievement is noteworthy because it includes the capture of a snailfish species known as Pseudoliparis belyaevi. Notably, this is the first time a fish has been collected from depths exceeding 8,000 meters, as these snailfish were previously observed solely at a shallower depth of 7,703 meters.

Historic Vids

13,716,052 次观看 • 3 年前

Upscale-A-Video was just released and it's so good! 🤯 It's a temporal-consistent Diffusion Model for video Super-Resolution, and has some of the best results I've ever seen, look at how sharp those lines become! More details below ⬇️⬇️

Upscale-A-Video was just released and it's so good! 🤯 It's a temporal-consistent Diffusion Model for video Super-Resolution, and has some of the best results I've ever seen, look at how sharp those lines become! More details below ⬇️⬇️

Alex Carlier

289,350 次观看 • 2 年前

Issue 4 of Interfaces just released! This issue is about building an animated sign-in dialog. It covers everything that goes into building it, from the animations to the small but important details. It's one of the most in-depth issues yet, full of code snippets and demos.

Issue 4 of Interfaces just released! This issue is about building an animated sign-in dialog. It covers everything that goes into building it, from the animations to the small but important details. It's one of the most in-depth issues yet, full of code snippets and demos.

Jakub Krehel

37,341 次观看 • 2 个月前

I just want to show you what an explosion of 1000 kg of explosives looks like at a depth of 20-30 meters. The video shows the destruction of a German bottom mine in the waters of the Feodosiysky Bay in the Crimea.

I just want to show you what an explosion of 1000 kg of explosives looks like at a depth of 20-30 meters. The video shows the destruction of a German bottom mine in the waters of the Feodosiysky Bay in the Crimea.

Capt(N)

147,641 次观看 • 1 年前

We’re thrilled to announce our Innovation Showcase programme! From 28-29 September, we’ll be joined by inspirational leaders in the creative industries for thought-provoking panels, in-depth conversations and special performances ⬇️

We’re thrilled to announce our Innovation Showcase programme! From 28-29 September, we’ll be joined by inspirational leaders in the creative industries for thought-provoking panels, in-depth conversations and special performances ⬇️

Creative Informatics

11,988 次观看 • 2 年前

We just revamped session key management for the Abstract Global Wallet. You can now see in-depth details on what session keys and permissions are active for apps that you've used. This will make wallet management more secure and transparent for all users going forward.

We just revamped session key management for the Abstract Global Wallet. You can now see in-depth details on what session keys and permissions are active for apps that you've used. This will make wallet management more secure and transparent for all users going forward.

cygaar

21,582 次观看 • 6 个月前

An update for everyone who is not in our Discord... Obviously we are still early in development, and our team has been working hard to release updates for everyone to see. We have a peak at the terrain, which is this picture is based of the North Dakota drift prairie, Great care, time and effort was put into the terrain to create smooth rolling hills, the road network in this region will be challenging, just as it is in real life. From Will The current state of the TIV2 model, which will include a lot more in depth details, From Jlkillen03 The stages of damage to a Blender made house, From Kunahic And how texturing will be used for assets like the interiors! From BSP

An update for everyone who is not in our Discord... Obviously we are still early in development, and our team has been working hard to release updates for everyone to see. We have a peak at the terrain, which is this picture is based of the North Dakota drift prairie, Great care, time and effort was put into the terrain to create smooth rolling hills, the road network in this region will be challenging, just as it is in real life. From Will The current state of the TIV2 model, which will include a lot more in depth details, From Jlkillen03 The stages of damage to a Blender made house, From Kunahic And how texturing will be used for assets like the interiors! From BSP

Severity

18,960 次观看 • 4 个月前

Depth video workflows have been getting a lot of attention lately, so I tested one myself. Combined with Seedance 2.0, it produced more natural motion-transfer results than using Kling Motion Control directly. Why use a depth video? 1. It removes the original character and scene details, reducing copyright and sensitive-content risks. 2. It preserves the original motion, timing, and spatial structure. This separates motion extraction from visual generation, allowing you to recreate the movement with better models and any reference character. We’ve also launched a free online tool that converts regular videos into depth videos—no local setup required: In the example below, we converted a dance video from Douyin into a depth video, then regenerated it with a reference character using Seedance 2.0. The original choreography and timing are preserved, while the lighting adapts naturally to the new character and scene.

Depth video workflows have been getting a lot of attention lately, so I tested one myself. Combined with Seedance 2.0, it produced more natural motion-transfer results than using Kling Motion Control directly. Why use a depth video? 1. It removes the original character and scene details, reducing copyright and sensitive-content risks. 2. It preserves the original motion, timing, and spatial structure. This separates motion extraction from visual generation, allowing you to recreate the movement with better models and any reference character. We’ve also launched a free online tool that converts regular videos into depth videos—no local setup required: In the example below, we converted a dance video from Douyin into a depth video, then regenerated it with a reference character using Seedance 2.0. The original choreography and timing are preserved, while the lighting adapts naturally to the new character and scene.

underwood

15,968 次观看 • 5 天前

“What more can we really do?” 🗣️ Just over 15,000 people attended this afternoon’s home tie against Watford - a similar number to last week’s game. 🫣 In episode 8 of the Only Swans Podcast, Carwyn and Oli discussed this issue in-depth and questioned what more could really be done in an already exciting period for the club. 🦢 ⬇️ Listen In Full ⬇️ 🔴 YouTube: 🟢 Spotify: 🟣 Apple Podcasts:

“What more can we really do?” 🗣️ Just over 15,000 people attended this afternoon’s home tie against Watford - a similar number to last week’s game. 🫣 In episode 8 of the Only Swans Podcast, Carwyn and Oli discussed this issue in-depth and questioned what more could really be done in an already exciting period for the club. 🦢 ⬇️ Listen In Full ⬇️ 🔴 YouTube: 🟢 Spotify: 🟣 Apple Podcasts:

Only Swans

14,978 次观看 • 11 个月前

I'll always root for a team that open-sources its best work, and Robbyant just did it properly. Robbyant, Ant Group's embodied-AI company, released LingBot-Vision, a vision foundation model for robots, and the part I love is the data. They trained it on 161M images, filtered down from 2B raw ones and mostly pulled straight from the open web, with no human labels, no edge detectors, no depth sensors anywhere in the loop. It learns the exact edges of objects from raw pixels. That's roughly a tenth of the data DINOv3 saw, and under a third of the training. And it shows in the results. On depth, working out how far away things are, the 1B model edges out a 7B on NYU-Depth. It also powers LingBot-Depth 2.0, which reads the surfaces cameras usually choke on, glass and mirrors, and halves indoor depth error. LingBot-Vision is fully open. Weights from the 1.1B flagship down to a tiny 21M version, code, and the paper. This is the timeline I want more of. Robbyant

I'll always root for a team that open-sources its best work, and Robbyant just did it properly. Robbyant, Ant Group's embodied-AI company, released LingBot-Vision, a vision foundation model for robots, and the part I love is the data. They trained it on 161M images, filtered down from 2B raw ones and mostly pulled straight from the open web, with no human labels, no edge detectors, no depth sensors anywhere in the loop. It learns the exact edges of objects from raw pixels. That's roughly a tenth of the data DINOv3 saw, and under a third of the training. And it shows in the results. On depth, working out how far away things are, the 1B model edges out a 7B on NYU-Depth. It also powers LingBot-Depth 2.0, which reads the surfaces cameras usually choke on, glass and mirrors, and halves indoor depth error. LingBot-Vision is fully open. Weights from the 1.1B flagship down to a tiny 21M version, code, and the paper. This is the timeline I want more of. Robbyant

Chubby♨️

48,249 次观看 • 1 个月前

Ecom Brands I spent more than 100 hours making an entire masterclass about Advertising on Meta and Google. The most in depth content I have ever released for FREE. RT & Comment "Masterclass" and I will send it to you. (Must be following)

Ecom Brands I spent more than 100 hours making an entire masterclass about Advertising on Meta and Google. The most in depth content I have ever released for FREE. RT & Comment "Masterclass" and I will send it to you. (Must be following)

Luke Bielby

248,721 次观看 • 2 年前

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.

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 次观看 • 8 个月前