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。

Are we done with object detection? What about tiny objects beyond 200 meters? 🔎 Telescope 🔭 addresses long-range perception by explicitly tackling extreme scale imbalance ⚖️ in images. It hinges on a learnable hyperbolic foveation transform from a low-resolution image, magnifying distant regions 🔍 while compressing nearby ones -... show more

Felix Heide

1,951 subscribers

188,350 次观看 • 1 个月前 •via X (Twitter)

教育健康养生科学技术

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

Class XII Interceptor at 2000fps doing what they do.. These objects are flying by commercial aircraft on a routine basis. This was shot with a telescope and an attached high speed camera. This white object is in focus along with the aircraft. They are occupying the same space. These objects are doing this every day. I cannot show clearer footage, this shit is f'ing real. What are they doing and why are they doing it? Ross Coulthart Garry P. Nolan

Class XII Interceptor at 2000fps doing what they do.. These objects are flying by commercial aircraft on a routine basis. This was shot with a telescope and an attached high speed camera. This white object is in focus along with the aircraft. They are occupying the same space. These objects are doing this every day. I cannot show clearer footage, this shit is f'ing real. What are they doing and why are they doing it? Ross Coulthart Garry P. Nolan

ProPixel Video Analysis and Research

27,693 次观看 • 16 天前

Each line on that image represents a projection through an object with a different viewing angle, here's what you see when you project it back, you can get some idea of what the original image was, but it's very blurry.

Each line on that image represents a projection through an object with a different viewing angle, here's what you see when you project it back, you can get some idea of what the original image was, but it's very blurry.

Scott Manley

21,719 次观看 • 1 年前

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

apolinario (poli)

29,948 次观看 • 22 天前

RIP Photoshop. Higgsfield just launched Canvas, a state-of-the-art image editing model. With just two clicks, you can swap any object in an image. Logos, text, texture and scale stay exactly as they are... Here's how it works:

RIP Photoshop. Higgsfield just launched Canvas, a state-of-the-art image editing model. With just two clicks, you can swap any object in an image. Logos, text, texture and scale stay exactly as they are... Here's how it works:

Angry Tom

155,788 次观看 • 1 年前

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

PyCharm, a JetBrains IDE

34,908 次观看 • 1 个月前

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,801 次观看 • 1 年前

No objects in this image are moving 😳

No objects in this image are moving 😳

NO CONTEXT HUMANS

143,921 次观看 • 1 年前

Google Bard just changed the ChatGPT game with its massive multimodal upgrade - Image Recognition It doesn't just recognize objects in the image, it can also extract texts and understand the image. Here are 8 mind blowing examples:

Google Bard just changed the ChatGPT game with its massive multimodal upgrade - Image Recognition It doesn't just recognize objects in the image, it can also extract texts and understand the image. Here are 8 mind blowing examples:

Min Choi

1,286,073 次观看 • 2 年前

No objects in this image are moving [🎞️ jagarikin]

No objects in this image are moving [🎞️ jagarikin]

Massimo

237,424 次观看 • 1 年前

New feature✨ Rotate the bounding box to align with what you're transforming🔄 Resize, Free Transform, and Mesh Transform in the direction you want🔍

New feature✨ Rotate the bounding box to align with what you're transforming🔄 Resize, Free Transform, and Mesh Transform in the direction you want🔍

CLIP STUDIO PAINT

39,104 次观看 • 10 个月前

Terrain Scan Shader 🔎 This material adapts to a sphere mesh using Object Position and Radius making the scan effect seamlessly appear over other objects in your scene #gamedev #VFX #realtimeVFX #UnrealEngine

Terrain Scan Shader 🔎 This material adapts to a sphere mesh using Object Position and Radius making the scan effect seamlessly appear over other objects in your scene #gamedev #VFX #realtimeVFX #UnrealEngine

TUATARA

46,323 次观看 • 1 年前

Detect small objects using @Ultralytics YOLO26 + SAHI 😍 A perfect combo when speed isn’t the priority, but accuracy is everything, especially when detecting tiny or distant objects in your images. learn how it works 👇 #AI #objectdetection #trafficanalysis

Detect small objects using @Ultralytics YOLO26 + SAHI 😍 A perfect combo when speed isn’t the priority, but accuracy is everything, especially when detecting tiny or distant objects in your images. learn how it works 👇 #AI #objectdetection #trafficanalysis

Muhammad Rizwan Munawar

39,197 次观看 • 1 个月前

Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D diffusion model that explicitly models object articulation, paving the way for richer, more realistic assets in embodied AI and simulation: – Generates fully articulated 3D objects – Physically plausible joints & motion – High-fidelity 3D Gaussian appearance – Supports generation from a single real image arXiv: Project: Code (coming soon):

Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D diffusion model that explicitly models object articulation, paving the way for richer, more realistic assets in embodied AI and simulation: – Generates fully articulated 3D objects – Physically plausible joints & motion – High-fidelity 3D Gaussian appearance – Supports generation from a single real image arXiv: Project: Code (coming soon):

Xingang Pan

11,473 次观看 • 6 个月前

While tracking the Moon through a telescope in daylight, an unusual object appeared near the lunar surface during a brief observation. The exact nature of the object cannot be determined from a single recording, and multiple explanations may exist, including a meteoroid, satellite transit, or imaging effect. Observations like this are a reminder of how dynamic the space environment can be. A brief passage near the Moon... captured in broad daylight. #moon #astronomy #telescope #space #nasa

While tracking the Moon through a telescope in daylight, an unusual object appeared near the lunar surface during a brief observation. The exact nature of the object cannot be determined from a single recording, and multiple explanations may exist, including a meteoroid, satellite transit, or imaging effect. Observations like this are a reminder of how dynamic the space environment can be. A brief passage near the Moon... captured in broad daylight. #moon #astronomy #telescope #space #nasa

Physics-astronomy

19,618 次观看 • 11 天前

Future CSS Tip! 🤞 You could create an image zoom/crop using the CSS object-view-box property 🔍 img { object-fit: cover; object-view-box: inset( var(--top) var(--right) var(--bottom) var(--left) ); } CodePen.IO link below! 👇

Future CSS Tip! 🤞 You could create an image zoom/crop using the CSS object-view-box property 🔍 img { object-fit: cover; object-view-box: inset( var(--top) var(--right) var(--bottom) var(--left) ); } CodePen.IO link below! 👇

jhey ʕ•ᴥ•ʔ

167,991 次观看 • 2 年前

Another explanation for Oumuamua's unusual shape has been proposed The asteroid Oumuamua, which flew through the Solar System in 2017, amazed scientists with its unprecedentedly elongated shape. It is 230 meters long and about 35 meters wide. Astronomers have never seen such objects before and tried to explain its origin. Oumuamua is the first known object to arrive from interstellar space. Its trajectory and speed left no doubt that it does not belong to the Solar System. The object rotated around its axis, changing its brightness, which made it possible to determine its size.

Another explanation for Oumuamua's unusual shape has been proposed The asteroid Oumuamua, which flew through the Solar System in 2017, amazed scientists with its unprecedentedly elongated shape. It is 230 meters long and about 35 meters wide. Astronomers have never seen such objects before and tried to explain its origin. Oumuamua is the first known object to arrive from interstellar space. Its trajectory and speed left no doubt that it does not belong to the Solar System. The object rotated around its axis, changing its brightness, which made it possible to determine its size.

Black Hole

237,039 次观看 • 1 年前

Another explanation for Oumuamua's unusual shape has been proposed The asteroid Oumuamua, which flew through the Solar System in 2017, amazed scientists with its unprecedentedly elongated shape. It is 230 meters long and about 35 meters wide. Astronomers have never seen such objects before and tried to explain its origin. Oumuamua is the first known object to arrive from interstellar space. Its trajectory and speed left no doubt that it does not belong to the Solar System. The object rotated around its axis, changing its brightness, which made it possible to determine its size.

Another explanation for Oumuamua's unusual shape has been proposed The asteroid Oumuamua, which flew through the Solar System in 2017, amazed scientists with its unprecedentedly elongated shape. It is 230 meters long and about 35 meters wide. Astronomers have never seen such objects before and tried to explain its origin. Oumuamua is the first known object to arrive from interstellar space. Its trajectory and speed left no doubt that it does not belong to the Solar System. The object rotated around its axis, changing its brightness, which made it possible to determine its size.

Black Hole

77,373 次观看 • 1 年前

In Donkey Kong Bananza, DK follows objects of interest with his eyes. However, he has an incredibly short attention span. Whenever a new object enters his vision, his attention is drawn to it instead. If many objects are moving, he will be distracted by each new one.

In Donkey Kong Bananza, DK follows objects of interest with his eyes. However, he has an incredibly short attention span. Whenever a new object enters his vision, his attention is drawn to it instead. If many objects are moving, he will be distracted by each new one.

Supper Mario Broth

1,638,953 次观看 • 9 个月前

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering discuss: The correct insertion of virtual objects in images of real-world scenes requires a deep understanding of the scene's lighting, geometry and materials, as well as the image formation process. While recent large-scale diffusion models have shown strong generative and inpainting capabilities, we find that current models do not sufficiently "understand" the scene shown in a single picture to generate consistent lighting effects (shadows, bright reflections, etc.) while preserving the identity and details of the composited object. We propose using a personalized large diffusion model as guidance to a physically based inverse rendering process. Our method recovers scene lighting and tone-mapping parameters, allowing the photorealistic composition of arbitrary virtual objects in single frames or videos of indoor or outdoor scenes. Our physically based pipeline further enables automatic materials and tone-mapping refinement.

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering discuss: The correct insertion of virtual objects in images of real-world scenes requires a deep understanding of the scene's lighting, geometry and materials, as well as the image formation process. While recent large-scale diffusion models have shown strong generative and inpainting capabilities, we find that current models do not sufficiently "understand" the scene shown in a single picture to generate consistent lighting effects (shadows, bright reflections, etc.) while preserving the identity and details of the composited object. We propose using a personalized large diffusion model as guidance to a physically based inverse rendering process. Our method recovers scene lighting and tone-mapping parameters, allowing the photorealistic composition of arbitrary virtual objects in single frames or videos of indoor or outdoor scenes. Our physically based pipeline further enables automatic materials and tone-mapping refinement.

AK

19,101 次观看 • 1 年前

🎨 We're open sourcing 4 new LoRAs trained with new fal FLUX.2 [klein] 4B Trainer! 🖼️ Outpaint - Expand your images beyond borders 🔍 Zoom - Select an area and regenerate it enlarged 🧹 Object Remove - Clean removal of unwanted objects 🎭 Background Remove - Seamless background extraction Model weights are on Hugging Face

🎨 We're open sourcing 4 new LoRAs trained with new fal FLUX.2 [klein] 4B Trainer! 🖼️ Outpaint - Expand your images beyond borders 🔍 Zoom - Select an area and regenerate it enlarged 🧹 Object Remove - Clean removal of unwanted objects 🎭 Background Remove - Seamless background extraction Model weights are on Hugging Face

fal

27,717 次观看 • 4 个月前