Monocular depth estimation is a challenging task that predicts the pixel-wise depth from a single 2D image. Current methods typically model this problem as a regression or classification task. We propose DiffusionDepth, a new approach that reformulates monocular depth estimation as a denoising diffusion process. It learns an iterative denoising process to `denoise' random depth distribution into a depth map with the guidance of monocular visual conditions. The process is performed in the latent space encoded by a dedicated depth encoder and decoder. Instead of diffusing ground truth (GT) depth, the model learns to reverse the process of diffusing the refined depth of itself into random depth distribution. This self-diffusion formulation overcomes the difficulty of applying generative models to sparse GT depth scenarios. The proposed approach benefits this task by refining depth estimation step by step, which is superior for generating accurate and highly detailed depth maps. Experimental results on KITTI and NYU-Depth-V2 datasets suggest that a simple yet efficient diffusion approach could reach state-of-the-art performance in both indoor and outdoor scenarios with acceptable inference time.
相關內容
The introduction of audio latent diffusion models possessing the ability to generate realistic sound clips on demand from a text description has the potential to revolutionize how we work with audio. In this work, we make an initial attempt at understanding the inner workings of audio latent diffusion models by investigating how their audio outputs compare with the training data, similar to how a doctor auscultates a patient by listening to the sounds of their organs. Using text-to-audio latent diffusion models trained on the AudioCaps dataset, we systematically analyze memorization behavior as a function of training set size. We also evaluate different retrieval metrics for evidence of training data memorization, finding the similarity between mel spectrograms to be more robust in detecting matches than learned embedding vectors. In the process of analyzing memorization in audio latent diffusion models, we also discover a large amount of duplicated audio clips within the AudioCaps database.
The flourishing success of Deep Neural Networks(DNNs) on RGB-input perception tasks has opened unbounded possibilities for non-RGB-input perception tasks, such as object detection from wireless signals, lidar scans, and infrared images. Compared to the matured development pipeline of RGB-input (source modality) models, developing non-RGB-input (target-modality) models from scratch poses excessive challenges in the modality-specific network design/training tricks and labor in the target-modality annotation. In this paper, we propose ModAlity Calibration (MAC), an efficient pipeline for calibrating target-modality inputs to the DNN object detection models developed on the RGB (source) modality. We compose a target-modality-input model by adding a small calibrator module ahead of a source-modality model and introduce MAC training techniques to impose dense supervision on the calibrator. By leveraging (1) prior knowledge synthesized from the source-modality model and (2) paired {target, source} data with zero manual annotations, our target-modality models reach comparable or better metrics than baseline models that require 100% manual annotations. We demonstrate the effectiveness of MAC by composing the WiFi-input, Lidar-input, and Thermal-Infrared-input models upon the pre-trained RGB-input models respectively.
Existing methods for 3D tracking from monocular RGB videos predominantly consider articulated and rigid objects. Modelling dense non-rigid object deformations in this setting remained largely unaddressed so far, although such effects can improve the realism of the downstream applications such as AR/VR and avatar communications. This is due to the severe ill-posedness of the monocular view setting and the associated challenges. While it is possible to naively track multiple non-rigid objects independently using 3D templates or parametric 3D models, such an approach would suffer from multiple artefacts in the resulting 3D estimates such as depth ambiguity, unnatural intra-object collisions and missing or implausible deformations. Hence, this paper introduces the first method that addresses the fundamental challenges depicted above and that allows tracking human hands interacting with human faces in 3D from single monocular RGB videos. We model hands as articulated objects inducing non-rigid face deformations during an active interaction. Our method relies on a new hand-face motion and interaction capture dataset with realistic face deformations acquired with a markerless multi-view camera system. As a pivotal step in its creation, we process the reconstructed raw 3D shapes with position-based dynamics and an approach for non-uniform stiffness estimation of the head tissues, which results in plausible annotations of the surface deformations, hand-face contact regions and head-hand positions. At the core of our neural approach are a variational auto-encoder supplying the hand-face depth prior and modules that guide the 3D tracking by estimating the contacts and the deformations. Our final 3D hand and face reconstructions are realistic and more plausible compared to several baselines applicable in our setting, both quantitatively and qualitatively. //vcai.mpi-inf.mpg.de/projects/Decaf
We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give model insights beyond a simple performance ranking. To this end, we present MM-Vet, designed based on the insight that the intriguing ability to solve complicated tasks is often achieved by a generalist model being able to integrate different core vision-language (VL) capabilities. MM-Vet defines 6 core VL capabilities and examines the 16 integrations of interest derived from the capability combination. For evaluation metrics, we propose an LLM-based evaluator for open-ended outputs. The evaluator enables the evaluation across different question types and answer styles, resulting in a unified scoring metric. We evaluate representative LMMs on MM-Vet, providing insights into the capabilities of different LMM system paradigms and models. Code and data are available at //github.com/yuweihao/MM-Vet.
Recently, learned image compression has achieved remarkable performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in boosting rate-distortion performance. However, most entropy models only capture correlations in one dimension, while the latent representation contain channel-wise, local spatial, and global spatial correlations. To tackle this issue, we propose the Multi-Reference Entropy Model (MEM) and the advanced version, MEM$^+$. These models capture the different types of correlations present in latent representation. Specifically, We first divide the latent representation into slices. When decoding the current slice, we use previously decoded slices as context and employ the attention map of the previously decoded slice to predict global correlations in the current slice. To capture local contexts, we introduce two enhanced checkerboard context capturing techniques that avoids performance degradation. Based on MEM and MEM$^+$, we propose image compression models MLIC and MLIC$^+$. Extensive experimental evaluations demonstrate that our MLIC and MLIC$^+$ models achieve state-of-the-art performance, reducing BD-rate by $8.05\%$ and $11.39\%$ on the Kodak dataset compared to VTM-17.0 when measured in PSNR. Our code will be available at //github.com/JiangWeibeta/MLIC.
This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task. Different from prior HIC methods, our hierarchical prompting is the first to explicitly inject ancestor-class information as a tokenized hint that benefits the descendant-class discrimination. We think it well imitates human visual recognition, i.e., humans may use the ancestor class as a prompt to draw focus on the subtle differences among descendant classes. We model this prompting mechanism into a Transformer with Hierarchical Prompting (TransHP). TransHP consists of three steps: 1) learning a set of prompt tokens to represent the coarse (ancestor) classes, 2) on-the-fly predicting the coarse class of the input image at an intermediate block, and 3) injecting the prompt token of the predicted coarse class into the intermediate feature. Though the parameters of TransHP maintain the same for all input images, the injected coarse-class prompt conditions (modifies) the subsequent feature extraction and encourages a dynamic focus on relatively subtle differences among the descendant classes. Extensive experiments show that TransHP improves image classification on accuracy (e.g., improving ViT-B/16 by +2.83% ImageNet classification accuracy), training data efficiency (e.g., +12.69% improvement under 10% ImageNet training data), and model explainability. Moreover, TransHP also performs favorably against prior HIC methods, showing that TransHP well exploits the hierarchical information.
Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark for video generation requires data annotated over time, which contrasts with the single caption used often in video datasets. To fill this gap, we collect comprehensive human annotations on three existing datasets, and introduce StoryBench: a new, challenging multi-task benchmark to reliably evaluate forthcoming text-to-video models. Our benchmark includes three video generation tasks of increasing difficulty: action execution, where the next action must be generated starting from a conditioning video; story continuation, where a sequence of actions must be executed starting from a conditioning video; and story generation, where a video must be generated from only text prompts. We evaluate small yet strong text-to-video baselines, and show the benefits of training on story-like data algorithmically generated from existing video captions. Finally, we establish guidelines for human evaluation of video stories, and reaffirm the need of better automatic metrics for video generation. StoryBench aims at encouraging future research efforts in this exciting new area.
Many real-world prediction tasks have outcome variables that have characteristic heavy-tail distributions. Examples include copies of books sold, auction prices of art pieces, demand for commodities in warehouses, etc. By learning heavy-tailed distributions, "big and rare" instances (e.g., the best-sellers) will have accurate predictions. Most existing approaches are not dedicated to learning heavy-tailed distribution; thus, they heavily under-predict such instances. To tackle this problem, we introduce Learning to Place (L2P), which exploits the pairwise relationships between instances for learning. In its training phase, L2P learns a pairwise preference classifier: is instance A > instance B? In its placing phase, L2P obtains a prediction by placing the new instance among the known instances. Based on its placement, the new instance is then assigned a value for its outcome variable. Experiments on real data show that L2P outperforms competing approaches in terms of accuracy and ability to reproduce heavy-tailed outcome distribution. In addition, L2P provides an interpretable model by placing each predicted instance in relation to its comparable neighbors. Interpretable models are highly desirable when lives and treasure are at stake.
We present WinSyn, a dataset consisting of high-resolution photographs and renderings of 3D models as a testbed for synthetic-to-real research. The dataset consists of 75,739 high-resolution photographs of building windows, including traditional and modern designs, captured globally. These include 89,318 cropped subimages of windows, of which 9,002 are semantically labeled. Further, we present our domain-matched photorealistic procedural model which enables experimentation over a variety of parameter distributions and engineering approaches. Our procedural model provides a second corresponding dataset of 21,290 synthetic images. This jointly developed dataset is designed to facilitate research in the field of synthetic-to-real learning and synthetic data generation. WinSyn allows experimentation into the factors that make it challenging for synthetic data to compete with real-world data. We perform ablations using our synthetic model to identify the salient rendering, materials, and geometric factors pertinent to accuracy within the labeling task. We chose windows as a benchmark because they exhibit a large variability of geometry and materials in their design, making them ideal to study synthetic data generation in a constrained setting. We argue that the dataset is a crucial step to enable future research in synthetic data generation for deep learning.
We present CoDEx, a set of knowledge graph completion datasets extracted from Wikidata and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. In terms of scope, CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible but verified to be false. To characterize CoDEx, we contribute thorough empirical analyses and benchmarking experiments. First, we analyze each CoDEx dataset in terms of logical relation patterns. Next, we report baseline link prediction and triple classification results on CoDEx for five extensively tuned embedding models. Finally, we differentiate CoDEx from the popular FB15K-237 knowledge graph completion dataset by showing that CoDEx covers more diverse and interpretable content, and is a more difficult link prediction benchmark. Data, code, and pretrained models are available at //bit.ly/2EPbrJs.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191