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。

We present TeSMo ( ), a text-controlled scene-aware motion generation method based on denoising diffusion models. It’s an exciting collaboration with Justus Thies, Michael Black, Jason Peng, Davis Rempe. (1/7)

Hongwei Yi

3,148 subscribers

45,744 次观看 • 2 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

9 条评论

Hongwei Yi 的头像

Hongwei Yi2 年前

Given a 3D scene and a target interaction object, our goal is to generate a plausible human-scene interaction, where a user-specified text prompt can control the motion style. (2/7)

Hongwei Yi 的头像

Hongwei Yi2 年前

Since there are few datasets with motion, text, and 3D scenes together, we propose to fine-tune a powerful pre-trained text-to-motion motion with a new scene-aware branch. (3/7)

Hongwei Yi 的头像

Hongwei Yi2 年前

First, we pre-train a scene-agnostic text-to-motion diffusion model on a large motion-capture dataset, prioritizing learning to reach goal locations. Then, we augment it with a scene-aware component, finetuning with augmented data containing detailed scene information. (4/7)

Hongwei Yi 的头像

Hongwei Yi2 年前

We create the Loco-3D-Front dataset to learn navigation, by integrating locomotion sequences from HumanML3D into diverse 3D environments from 3D-FRONT. For interactions, we annotate text descriptions for sub-sequences from the SAMP dataset. (5/7)

Hongwei Yi 的头像

Hongwei Yi2 年前

Our method successfully generates realistic motions that navigate around obstacles while being conditioned on various text prompts. (6/7)

Hongwei Yi 的头像

Hongwei Yi2 年前

For interactions, diverse text descriptions help disambiguate between actions like sitting or standing up, and even allow for stylizing sitting motions, such as crossing arms. (7/7)

Siyuan Huang 的头像

Siyuan Huang2 年前

@JustusThies @Michael_J_Black @xbpeng4 @davrempe nice work, congrats!

Nicolas Keller 的头像

Nicolas Keller2 年前

@JustusThies @Michael_J_Black @xbpeng4 @davrempe Looks amazing - congrats!

Frank (Haofan) Wang 的头像

Frank (Haofan) Wang2 年前

@JustusThies @Michael_J_Black @xbpeng4 @davrempe 恭喜易老哥毕业🎓

相关视频

Dreamix: Video Diffusion Models are General Video Editors abs: project page: present diffusion-based method that is able to perform text-based motion and appearance editing of general videos

Dreamix: Video Diffusion Models are General Video Editors abs: project page: present diffusion-based method that is able to perform text-based motion and appearance editing of general videos

AK

398,258 次观看 • 3 年前

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 次观看 • 2 年前

Introducing 🔥BLIP-Diffusion🔥, a novel method for enabling Text-to-image Diffusion models with multimodal controllable generation/editing, powered by BLIP-2 pre-trained text-aligned subject representation. Paper: Project: (1/n)

Introducing 🔥BLIP-Diffusion🔥, a novel method for enabling Text-to-image Diffusion models with multimodal controllable generation/editing, powered by BLIP-2 pre-trained text-aligned subject representation. Paper: Project: (1/n)

Steven Hoi

40,615 次观看 • 3 年前

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

AI at Meta

798,500 次观看 • 3 年前

We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: #CVPR #AI #CVML👇

We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: #CVPR #AI #CVML👇

Tolga Birdal

16,795 次观看 • 1 年前

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,681 次观看 • 3 年前

📢 Diffusion models (DM) generate samples from noise distribution, but for tasks such as image-to-image translation, one side is no longer noise. We present Denoising Diffusion Bridge Models, a simple and scalable extension to DMs suitable for distribution translation problems.

📢 Diffusion models (DM) generate samples from noise distribution, but for tasks such as image-to-image translation, one side is no longer noise. We present Denoising Diffusion Bridge Models, a simple and scalable extension to DMs suitable for distribution translation problems.

Linqi (Alex) Zhou

111,661 次观看 • 3 年前

In 2022, we made a breakthrough in 2D jigsaw puzzles by diffusion models (Puzzle Fusion). Now, we make a breakthrough in 3D shape assembly with an auto-agglomerative approach based on diffusion models. Find the code, models, data, and paper at

In 2022, we made a breakthrough in 2D jigsaw puzzles by diffusion models (Puzzle Fusion). Now, we make a breakthrough in 3D shape assembly with an auto-agglomerative approach based on diffusion models. Find the code, models, data, and paper at

Yasutaka Furukawa

11,314 次观看 • 2 年前

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,557 次观看 • 3 年前

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

AK

82,138 次观看 • 3 年前

MotionStreamer announced on Hugging Face Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

MotionStreamer announced on Hugging Face Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

AK

43,422 次观看 • 1 年前

WorldExplorer: Towards Generating Fully Navigable 3D Scenes Contributions: • We introduce the first method for generating 3D scenes from text that supports high-quality view synthesis while enabling exploration across a wide range of camera poses. • We propose an iterative scene expansion strategy using video diffusion models, driven by trajectory sampling and adaptive collision detection. • We design a scene memory mechanism that conditions each video generation step on relevant past frames, improving view consistency and overall scene coherence.

WorldExplorer: Towards Generating Fully Navigable 3D Scenes Contributions: • We introduce the first method for generating 3D scenes from text that supports high-quality view synthesis while enabling exploration across a wide range of camera poses. • We propose an iterative scene expansion strategy using video diffusion models, driven by trajectory sampling and adaptive collision detection. • We design a scene memory mechanism that conditions each video generation step on relevant past frames, improving view consistency and overall scene coherence.

MrNeRF

23,814 次观看 • 1 年前

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,654 次观看 • 2 年前

$DreamScene360 Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360^{circ} scene generation pipeline$

DreamScene360 Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360^{circ} scene generation pipeline

AK

24,910 次观看 • 2 年前

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.

AK

30,450 次观看 • 2 年前

Oh wow! "[SIGGRAPH '24] DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models" Paper: Project: Code (MIT) :

Oh wow! "[SIGGRAPH '24] DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models" Paper: Project: Code (MIT) :

MrNeRF

59,794 次观看 • 2 年前

(1/2) LightIt: Illumination Modeling and Control for Diffusion Models! #CVPR2024 We facilitate lighting control for novel image generation from text prompts. We can also edit lighting for a given input image. Video: Project:

(1/2) LightIt: Illumination Modeling and Control for Diffusion Models! #CVPR2024 We facilitate lighting control for novel image generation from text prompts. We can also edit lighting for a given input image. Video: Project:

Matthias Niessner

19,849 次观看 • 2 年前

Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models paper page: Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models. Despite great promise, video diffusion models are difficult to control, hindering a user to apply their own creativity rather than amplifying it. To address this challenge, we present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. For this purpose, our approach takes an animated, low-fidelity rendered mesh as input and injects the ground truth correspondence information obtained from the dynamic mesh into various stages of a pre-trained text-to-image generation model to output high-quality and temporally consistent frames. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.

Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models paper page: Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models. Despite great promise, video diffusion models are difficult to control, hindering a user to apply their own creativity rather than amplifying it. To address this challenge, we present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. For this purpose, our approach takes an animated, low-fidelity rendered mesh as input and injects the ground truth correspondence information obtained from the dynamic mesh into various stages of a pre-trained text-to-image generation model to output high-quality and temporally consistent frames. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.

AK

117,091 次观看 • 2 年前

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10

Xindi Wu

145,736 次观看 • 9 个月前