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。

Can we use motion to prompt diffusion models? Our #ICLR2024 paper does just that. We propose Motion Guidance, a technique that allows users to edit an image by specifying “where things should move.”

Daniel Geng

1,512 subscribers

16,306 次观看 • 2 年前 •via X (Twitter)

艺术科学技术教育 #ICLR2024

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

Can you make a jigsaw puzzle with two different solutions? Or an image that changes appearance when flipped? We can do that, and a lot more, by using diffusion models to generate optical illusions! Continue reading for more illusions and method details 🧵

Can you make a jigsaw puzzle with two different solutions? Or an image that changes appearance when flipped? We can do that, and a lot more, by using diffusion models to generate optical illusions! Continue reading for more illusions and method details 🧵

Daniel Geng

125,893 次观看 • 2 年前

This technique, called "shaving", where the motion man takes a step or two forward prior to the snap, was brought to the attention of teams by Walt Anderson that this is an illegal motion penalty. Called twice tonight.

This technique, called "shaving", where the motion man takes a step or two forward prior to the snap, was brought to the attention of teams by Walt Anderson that this is an illegal motion penalty. Called twice tonight.

 Fᴏᴏᴛʙᴀʟʟ Zᴇʙʀᴀs🇺🇦

10,440 次观看 • 1 年前

My first PhD paper!🎉We learn *diffusion* models for code generation that learn to directly *edit* syntax trees of programs. The result is a system that can incrementally write code, see the execution output, and debug it. 🧵1/n

My first PhD paper!🎉We learn diffusion models for code generation that learn to directly edit syntax trees of programs. The result is a system that can incrementally write code, see the execution output, and debug it. 🧵1/n

Shreyas Kapur

742,578 次观看 • 2 年前

'Once we understand the mechanics of the natural swing motion, we can use the natural laws to our advantage. Then we can give up the controls. 'Then we can fly.' George Knudson

'Once we understand the mechanics of the natural swing motion, we can use the natural laws to our advantage. Then we can give up the controls. 'Then we can fly.' George Knudson

Straight Down The Middle

122,343 次观看 • 1 年前

Garment3DGen 3D Garment Stylization and Texture Generation We introduce Garment3DGen a new method to synthesize 3D garment assets from a base mesh given a single input image as guidance. Our proposed approach allows users to generate 3D textured clothes based on both

Garment3DGen 3D Garment Stylization and Texture Generation We introduce Garment3DGen a new method to synthesize 3D garment assets from a base mesh given a single input image as guidance. Our proposed approach allows users to generate 3D textured clothes based on both

AK

53,149 次观看 • 2 年前

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

AK

41,830 次观看 • 3 年前

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

MrNeRF

24,729 次观看 • 1 年前

Diffusion models are great, but we can squeeze out so much more from them. The only problem is that it usually requires extra training or manual representation editing. In our new paper, we show that with the current capabilities of LLMs, it is much simpler than we thought!

Diffusion models are great, but we can squeeze out so much more from them. The only problem is that it usually requires extra training or manual representation editing. In our new paper, we show that with the current capabilities of LLMs, it is much simpler than we thought!

Yossi Gandelsman

34,899 次观看 • 5 个月前

Well seeing as y'all liked that previous image I shared from Halo 3: ODST's The Life/We Are ODST in motion. I guess I should show the Brute in motion I also found! This is seemingly tied to the deleted scene from the trailer!

Well seeing as y'all liked that previous image I shared from Halo 3: ODST's The Life/We Are ODST in motion. I guess I should show the Brute in motion I also found! This is seemingly tied to the deleted scene from the trailer!

Chris Aiken

436,121 次观看 • 9 个月前

How far can you get by simply specifying that an object move? With contact-implicit MPC, quite far! Will Yang's paper "Dynamic On-Palm Manipulation via Controlled Sliding," accepted to #rss2024 pushes the limits of real-time dexterity.

How far can you get by simply specifying that an object move? With contact-implicit MPC, quite far! Will Yang's paper "Dynamic On-Palm Manipulation via Controlled Sliding," accepted to #rss2024 pushes the limits of real-time dexterity.

Michael Posa

10,474 次观看 • 2 年前

Break-A-Scene: Extracting Multiple Concepts from a Single Image introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method paper page:

Break-A-Scene: Extracting Multiple Concepts from a Single Image introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method paper page:

AK

154,511 次观看 • 3 年前

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

Ricardo Martin-Brualla

21,685 次观看 • 1 年前

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.

NVIDIA AI

28,359 次观看 • 2 个月前

🚨 Wan Motion is now live on fal ! An optimized version of Wan 2.2 Animate. 🎬 Transfer motion from any driving video to a single reference image 🎭 Built-in motion retargeting, adapts to different body proportions ✨ Optional Flux 2 Edit identity enhancement for sharper character preservation 💸 Just $0.06/s for 720p, the cheapest motion transfer API available

🚨 Wan Motion is now live on fal ! An optimized version of Wan 2.2 Animate. 🎬 Transfer motion from any driving video to a single reference image 🎭 Built-in motion retargeting, adapts to different body proportions ✨ Optional Flux 2 Edit identity enhancement for sharper character preservation 💸 Just $0.06/s for 720p, the cheapest motion transfer API available

fal

13,253 次观看 • 6 个月前

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,867 次观看 • 2 年前

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a discrete diffusion objective. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.

Mihir Prabhudesai

104,934 次观看 • 1 年前

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,062 次观看 • 1 年前

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵

Jialu Li

35,060 次观看 • 1 年前

We release Diamond Maps💎 unlocking accurate and efficient guidance for diffusion models. Our experiments show that our methods scale incredibly well. Excited to see what people will build with this! Accurate guidance has been a notoriously hard problem, but in this work, we’re bringing TWO (!) solutions to the table. The recipe for success: 1️⃣ Speed: Use distilled models (flow maps, mean flows, consistency models). 2️⃣ Exploration: Inject stochasticity to properly explore your search space. Because this fundamentally improves anything using flow matching and diffusion, we see a lot of potential for applications across audio, robotics, molecules, and beyond. Paper: Code: Huge thanks to an amazing team: Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong (Kelly) He, Zeynep Akata, Tommi Jaakkola, Nicholas Boffi, and Max Simchowitz. It was awesome bringing this to life together!

We release Diamond Maps💎 unlocking accurate and efficient guidance for diffusion models. Our experiments show that our methods scale incredibly well. Excited to see what people will build with this! Accurate guidance has been a notoriously hard problem, but in this work, we’re bringing TWO (!) solutions to the table. The recipe for success: 1️⃣ Speed: Use distilled models (flow maps, mean flows, consistency models). 2️⃣ Exploration: Inject stochasticity to properly explore your search space. Because this fundamentally improves anything using flow matching and diffusion, we see a lot of potential for applications across audio, robotics, molecules, and beyond. Paper: Code: Huge thanks to an amazing team: Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong (Kelly) He, Zeynep Akata, Tommi Jaakkola, Nicholas Boffi, and Max Simchowitz. It was awesome bringing this to life together!

Peter Holderrieth

60,526 次观看 • 4 个月前

📢MoRight: Motion Control Done Right "What if your video model actually understood cause and effect?" Existing motion-controlled video models entangle camera and object motion, and treat everything as kinematic displacement. MoRight changes both. 🔥 Motion Causality — MoRight decomposes motion into actions & consequences. Give an action → MoRight predicts consequences (aka motion simulation) . Give a desired outcome → MoRight recovers the driving action (aka motion planning). Not merely displacing pixels. 🎬 Disentangled Control — MoRight separates camera and object motion, allowing users to independently control each of them. No entanglement. Project Page: Paper:

📢MoRight: Motion Control Done Right "What if your video model actually understood cause and effect?" Existing motion-controlled video models entangle camera and object motion, and treat everything as kinematic displacement. MoRight changes both. 🔥 Motion Causality — MoRight decomposes motion into actions & consequences. Give an action → MoRight predicts consequences (aka motion simulation) . Give a desired outcome → MoRight recovers the driving action (aka motion planning). Not merely displacing pixels. 🎬 Disentangled Control — MoRight separates camera and object motion, allowing users to independently control each of them. No entanglement. Project Page: Paper:

Shaowei Liu

32,037 次观看 • 4 个月前