Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Accepted by #CVPR2023! X-Decoder is the FIRST generalist decoder that supports all segmentation tasks (ins/sem/pano/ref) in OPEN VOCABULARY, both inter- AND intra-image VL tasks, and even helps instruct image inpainting/editing! New demo below and more at

Jianwei Yang

3,979 subscribers

51,930 views • 3 years ago •via X (Twitter)

Education Science & Technology News & Politics #CVPR2023

Anya Rossi• Live Now

Private livecam show

6 Comments

Jianwei Yang3 years ago

This project was led by our two wonderful interns @xueyanzou1, @ZiYiDou! With joint mentorship from @zhegan4, @LINJIEFUN, @ChunyuanLi, Xiyang Dai, @HarkiratBehl, Jianfeng Wang, and senior advisory from Violet Peng, Lu Yuan, Lijuan Wang, @yong_jae_lee and @JianfengGao0217!

Akarsh G3 years ago

Used your instruct demo. Still not perfect.

Naoto Usuyama3 years ago

Congrats!

Dan Benyamin (Æ)3 years ago

Cc @levelsio

Akarsh G3 years ago

How is it different from pix2pix?

Jianwei Yang3 years ago

We used our x-decoder as a plug into the original pix2pix to make the edit more grounded.

Related Videos

🤯 OneDiffusion: A versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. ✅ Text to Image ✅ Image to Depth ✅ Image to Segmentation ✅ Image to Pose ✅ FaceID ✅ Image to Multiview How to use & more👇

🤯 OneDiffusion: A versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. ✅ Text to Image ✅ Image to Depth ✅ Image to Segmentation ✅ Image to Pose ✅ FaceID ✅ Image to Multiview How to use & more👇

Gradio

11,820 views • 1 year ago

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

AK

305,560 views • 2 years ago

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

AI at Meta

186,324 views • 3 years ago

Qwen-Image-Edit is out in anycoder for image editing in your vibe coded apps Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.

Qwen-Image-Edit is out in anycoder for image editing in your vibe coded apps Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.

AK

119,012 views • 9 months ago

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Xenova

88,743 views • 1 year ago

Track Anything: Segment Anything Meets Videos Track-Anything is a flexible and interactive tool for video object tracking and segmentation suitable for: - Video object tracking and segmentation with shot changes. - Visualized development and data annnotation for video object tracking and segmentation. - Object-centric downstream video tasks, such as video inpainting and editing. abs: github:

Track Anything: Segment Anything Meets Videos Track-Anything is a flexible and interactive tool for video object tracking and segmentation suitable for: - Video object tracking and segmentation with shot changes. - Visualized development and data annnotation for video object tracking and segmentation. - Object-centric downstream video tasks, such as video inpainting and editing. abs: github:

AK

578,577 views • 3 years ago

MagicSketch 🤩 Interactive image editing Gradio app. 🤯 An MLLM even infers editing intent in real-time and generates a prompt for inpainting for you!

MagicSketch 🤩 Interactive image editing Gradio app. 🤯 An MLLM even infers editing intent in real-time and generates a prompt for inpainting for you!

Gradio

39,802 views • 1 year ago

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

Matthias Niessner

18,808 views • 7 months ago

Segment Anything is fun and powerful but still requires full mask annotation for supervised training. Our new work MaskFreeVIS appearing at #CVPR2023 shows we can get accurate video instance segmentation WITHOUT any video or image mask annotations. More at

Segment Anything is fun and powerful but still requires full mask annotation for supervised training. Our new work MaskFreeVIS appearing at #CVPR2023 shows we can get accurate video instance segmentation WITHOUT any video or image mask annotations. More at

Fisher Yu

41,103 views • 3 years ago

New: Gemini 2.0 Flash native image generation! This bot supports image output and conversational editing, allowing you to create and refine images by describing what you want. (1/3)

New: Gemini 2.0 Flash native image generation! This bot supports image output and conversational editing, allowing you to create and refine images by describing what you want. (1/3)

Poe

18,992 views • 1 year ago

Seedream 4 arrived to Krea. this new model is competitive with Nano Banana for image editing and supports native 4k resolution. try it now in Krea Image!

Seedream 4 arrived to Krea. this new model is competitive with Nano Banana for image editing and supports native 4k resolution. try it now in Krea Image!

KREA AI

52,130 views • 9 months ago

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,190 views • 3 years ago

[1/2] We’ve released the code for #pix2pixturbo and #CycleGANTurbo. These conditional GANs are able to adapt a text-to-image model such as SD-Turbo for both paired and unpaired image translation with a single step (0.11 sec on A100 and 0.29 sec on A6000). Try our code and the Gradio demo. Paper: Code: Demo: This is a joint work with Gaurav Parmar (the leading author), Taesung Park, and Srinivasa Narasimhan. This work shows that a pre-trained one-step model can be easily adapted to conditional GANs frameworks for downstream image editing and synthesis tasks. #Edges2Cats

[1/2] We’ve released the code for #pix2pixturbo and #CycleGANTurbo. These conditional GANs are able to adapt a text-to-image model such as SD-Turbo for both paired and unpaired image translation with a single step (0.11 sec on A100 and 0.29 sec on A6000). Try our code and the Gradio demo. Paper: Code: Demo: This is a joint work with Gaurav Parmar (the leading author), Taesung Park, and Srinivasa Narasimhan. This work shows that a pre-trained one-step model can be easily adapted to conditional GANs frameworks for downstream image editing and synthesis tasks. #Edges2Cats

Jun-Yan Zhu

36,473 views • 2 years ago

So Alibaba Qwen has released the best image editing model... 100% open source! You can edit any photo using natural language. It can be used both locally and online. More below

So Alibaba Qwen has released the best image editing model... 100% open source! You can edit any photo using natural language. It can be used both locally and online. More below

Paul Couvert

246,474 views • 9 months ago

Just published official Cursor Rules so you can now 1-shot create your Trigger tasks: - Supports regular, scheduled and schema tasks - Realtime - Build extensions - Metadata - And more… Link below ↓

Just published official Cursor Rules so you can now 1-shot create your Trigger tasks: - Supports regular, scheduled and schema tasks - Realtime - Build extensions - Metadata - And more… Link below ↓

Trigger.dev

39,511 views • 1 year ago

Get your AI agents to collaborate. The Agent2Agent (A2A) protocol is a new open standard that helps agents interoperate and break up complex tasks across specialists.

Get your AI agents to collaborate. The Agent2Agent (A2A) protocol is a new open standard that helps agents interoperate and break up complex tasks across specialists.

Google for Developers

14,932 views • 7 months ago

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

AI at Meta

121,502 views • 1 year ago

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians Contributions: • We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models. • We introduce the concept of Super-Gaussian, a novel representation that integrates hierarchical instance segmentation features, enabling the embedding of high-dimensional language features. This approach addresses previously unfeasible challenges in representing complex scenes with rich semantic details. • Extensive experiments on the LERF-OVS and ScanNet datasets demonstrate the effectiveness of the proposed method, achieving significant improvements in open-vocabulary 3D object-level and scene-level semantic segmentation. It shows particular strength in capturing fine-grained scene details and dense pixel semantic segmentation tasks for the first time.

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians Contributions: • We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models. • We introduce the concept of Super-Gaussian, a novel representation that integrates hierarchical instance segmentation features, enabling the embedding of high-dimensional language features. This approach addresses previously unfeasible challenges in representing complex scenes with rich semantic details. • Extensive experiments on the LERF-OVS and ScanNet datasets demonstrate the effectiveness of the proposed method, achieving significant improvements in open-vocabulary 3D object-level and scene-level semantic segmentation. It shows particular strength in capturing fine-grained scene details and dense pixel semantic segmentation tasks for the first time.

MrNeRF

13,594 views • 1 year ago

Google is offering a Generative AI Learning Path with 10 courses for FREE! - Intro to Generative AI - Intro to LLMs - Intro to Image Generation - Encoder-Decoder Architecture - Transformer Models and more A Thread 🧵👇

Google is offering a Generative AI Learning Path with 10 courses for FREE! - Intro to Generative AI - Intro to LLMs - Intro to Image Generation - Encoder-Decoder Architecture - Transformer Models and more A Thread 🧵👇

Afiz ⚡️

249,513 views • 2 years ago

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

Jiasen Lu

33,383 views • 1 year ago