Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image. As permutations of instance IDs are also valid solutions, the task requires learning of high-dimensional one-to-many mapping. As a result, state-of-the-art approaches use customized architectures and task-specific loss functions. We formulate panoptic segmentation as a discrete data generation problem, without relying on inductive bias of the task. A diffusion model based on analog bits is used to model panoptic masks, with a simple, generic architecture and loss function. By simply adding past predictions as a conditioning signal, our method is capable of modeling video (in a streaming setting) and thereby learns to track object instances automatically. With extensive experiments, we demonstrate that our generalist approach can perform competitively to state-of-the-art specialist methods in similar settings.

尽管语言任务自然而然地以单个，统一的建模框架（即生成代币序列）表示，但在计算机视觉中并非如此。结果，对于不同的视力任务，不同的架构和损失功能的扩散。在这项工作中，我们表明，如果根据共享像素到序列界面进行配制，也可以统一一组“核心”计算机视觉任务。我们专注于四个任务，即对象检测，实例分割，关键点检测和图像字幕，所有这些任务都具有各种类型的输出，例如边界框或密集的掩码。尽管如此，通过将每个任务的输出作为具有统一界面的离散令牌的顺序，我们表明可以在所有这些任务上训练具有单个模型体系结构和损失功能的神经网络，而没有特定于任务的自定义。为了解决特定的任务，我们使用一个简短的提示作为任务说明，序列输出适应提示，以便它可以产生特定于任务的输出。我们表明，与成熟的特定任务模型相比，这种模型可以实现竞争性能。

生成时间连贯的高保真视频是生成建模研究中的重要里程碑。我们通过提出一个视频生成的扩散模型来取得这一里程碑的进步，该模型显示出非常有希望的初始结果。我们的模型是标准图像扩散体系结构的自然扩展，它可以从图像和视频数据中共同训练，我们发现这可以减少Minibatch梯度的方差并加快优化。为了生成长而更高的分辨率视频，我们引入了一种新的条件抽样技术，用于空间和时间视频扩展，该技术的性能比以前提出的方法更好。我们介绍了大型文本条件的视频生成任务，以及最新的结果，以实现视频预测和无条件视频生成的确定基准。可从https://video-diffusion.github.io/获得补充材料

我们使用条件扩散模型介绍调色板，这是一种简单而一般的框架，可用于图像到图像到图像转换。在四个具有挑战性的图像到图像转换任务（着色，染色，un折叠和JPEG减压），调色板优于强大的GaN和回归基线，并建立了新的最新状态。这是在没有特定于任务特定的超参数调整，架构定制或任何辅助损耗的情况下实现的，展示了理想的一般性和灵活性。我们揭示了使用$ l_2 $与vs. $ l_1 $损失在样本多样性上的越来越多的影响，并通过经验架构研究表明自我关注的重要性。重要的是，我们倡导基于想象项目的统一评估协议，并报告包括预先训练的Reset-50的FID，成立得分，分类准确度的多个样本质量评分，以及针对各种基线的参考图像的感知距离。我们预计这一标准化评估协议在推进图像到图像翻译研究方面发挥着关键作用。最后，我们表明，在3个任务（着色，染色，JPEG减压）上培训的单个通用调色板模型也表现或优于特定于任务专家的专家对应物。

我们表明，级联扩散模型能够在类条件的想象生成基准上生成高保真图像，而无需辅助图像分类器的任何帮助来提高样品质量。级联的扩散模型包括多个扩散模型的流水线，其产生越来越多的分辨率，以最低分辨率的标准扩散模型开始，然后是一个或多个超分辨率扩散模型，其连续上追随图像并添加更高的分辨率细节。我们发现级联管道的样本质量至关重要的是调节增强，我们提出的数据增强较低分辨率调节输入到超级分辨率模型的方法。我们的实验表明，调节增强防止在级联模型中采样过程中的复合误差，帮助我们在256×256分辨率下，在128x128和4.88，优于63.02的分类精度分数，培训级联管道。 ％（TOP-1）和84.06％（TOP-5）在256x256，优于VQ-VAE-2。

Springs are efficient in storing and returning elastic potential energy but are unable to hold the energy they store in the absence of an external load. Lockable springs use clutches to hold elastic potential energy in the absence of an external load but have not yet been widely adopted in applications, partly because clutches introduce design complexity, reduce energy efficiency, and typically do not afford high-fidelity control over the energy stored by the spring. Here, we present the design of a novel lockable compression spring that uses a small capstan clutch to passively lock a mechanical spring. The capstan clutch can lock up to 1000 N force at any arbitrary deflection, unlock the spring in less than 10 ms with a control force less than 1 % of the maximal spring force, and provide an 80 % energy storage and return efficiency (comparable to a highly efficient electric motor operated at constant nominal speed). By retaining the form factor of a regular spring while providing high-fidelity locking capability even under large spring forces, the proposed design could facilitate the development of energy-efficient spring-based actuators and robots.

Springs can provide force at zero net energy cost by recycling negative mechanical work to benefit motor-driven robots or spring-augmented humans. However, humans have limited force and range of motion, and motors have a limited ability to produce force. These limits constrain how much energy a conventional spring can store and, consequently, how much assistance a spring can provide. In this paper, we introduce an approach to accumulating negative work in assistive springs over several motion cycles. We show that, by utilizing a novel floating spring mechanism, the weight of a human or robot can be used to iteratively increase spring compression, irrespective of the potential energy stored by the spring. Decoupling the force required to compress a spring from the energy stored by a spring advances prior works, and could enable spring-driven robots and humans to perform physically demanding tasks without the use of large actuators.

We present the Recurrent Interface Network (RIN), a neural net architecture that allocates computation adaptively to the input according to the distribution of information, allowing it to scale to iterative generation of high-dimensional data. Hidden units of RINs are partitioned into the interface, which is locally connected to inputs, and latents, which are decoupled from inputs and can exchange information globally. The RIN block selectively reads from the interface into latents for high-capacity processing, with incremental updates written back to the interface. Stacking multiple blocks enables effective routing across local and global levels. While routing adds overhead, the cost can be amortized in recurrent computation settings where inputs change gradually while more global context persists, such as iterative generation using diffusion models. To this end, we propose a latent self-conditioning technique that "warm-starts" the latents at each iteration of the generation process. When applied to diffusion models operating directly on pixels, RINs yield state-of-the-art image and video generation without cascades or guidance, while being domain-agnostic and up to 10$\times$ more efficient compared to specialized 2D and 3D U-Nets.

Wearable sensors for measuring head kinematics can be noisy due to imperfect interfaces with the body. Mouthguards are used to measure head kinematics during impacts in traumatic brain injury (TBI) studies, but deviations from reference kinematics can still occur due to potential looseness. In this study, deep learning is used to compensate for the imperfect interface and improve measurement accuracy. A set of one-dimensional convolutional neural network (1D-CNN) models was developed to denoise mouthguard kinematics measurements along three spatial axes of linear acceleration and angular velocity. The denoised kinematics had significantly reduced errors compared to reference kinematics, and reduced errors in brain injury criteria and tissue strain and strain rate calculated via finite element modeling. The 1D-CNN models were also tested on an on-field dataset of college football impacts and a post-mortem human subject dataset, with similar denoising effects observed. The models can be used to improve detection of head impacts and TBI risk evaluation, and potentially extended to other sensors measuring kinematics.