This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architecture for fast feed-forward 3D generation, producing 3D mesh from a single image in under 0.5 seconds. Building upon the LRM network architecture, TripoSR integrates substantial improvements in data processing, model design, and training techniques. Evaluations on public datasets show that TripoSR exhibits superior performance, both quantitatively and qualitatively, compared to other open-source alternatives. Released under the MIT license, TripoSR is intended to empower researchers, developers, and creatives with the latest advancements in 3D generative AI.
Text-driven 3D scene generation techniques have made rapid progress in recent years. Their success is mainly attributed to using existing generative models to iteratively perform image warping and inpainting to generate 3D scenes. However, these methods heavily rely on the outputs of existing models, leading to error accumulation in geometry and appearance that prevent the models from being used in various scenarios (e.g., outdoor and unreal scenarios). To address this limitation, we generatively refine the newly generated local views by querying and aggregating global 3D information, and then progressively generate the 3D scene. Specifically, we employ a tri-plane features-based NeRF as a unified representation of the 3D scene to constrain global 3D consistency, and propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior from 2D diffusion model as well as the global 3D information of the current scene. Our extensive experiments demonstrate that, in comparison to previous methods, our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency.
We present LayerDiffuse, an approach enabling large-scale pretrained latent diffusion models to generate transparent images. The method allows generation of single transparent images or of multiple transparent layers. The method learns a "latent transparency" that encodes alpha channel transparency into the latent manifold of a pretrained latent diffusion model. It preserves the production-ready quality of the large diffusion model by regulating the added transparency as a latent offset with minimal changes to the original latent distribution of the pretrained model. In this way, any latent diffusion model can be converted into a transparent image generator by finetuning it with the adjusted latent space. We train the model with 1M transparent image layer pairs collected using a human-in-the-loop collection scheme. We show that latent transparency can be applied to different open source image generators, or be adapted to various conditional control systems to achieve applications like foreground/background-conditioned layer generation, joint layer generation, structural control of layer contents, etc. A user study finds that in most cases (97%) users prefer our natively generated transparent content over previous ad-hoc solutions such as generating and then matting. Users also report the quality of our generated transparent images is comparable to real commercial transparent assets like Adobe Stock.
Advances in Tiny Machine Learning (TinyML) have bolstered the creation of smart industry solutions, including smart agriculture, healthcare and smart cities. Whilst related research contributes to enabling TinyML solutions on constrained hardware, there is a need to amplify real-world applications by optimising energy consumption in battery-powered systems. The work presented extends and contributes to TinyML research by optimising battery-powered image-based anomaly detection Internet of Things (IoT) systems. Whilst previous work in this area has yielded the capabilities of on-device inferencing and training, there has yet to be an investigation into optimising the management of such capabilities using machine learning approaches, such as Reinforcement Learning (RL), to improve the deployment battery life of such systems. Using modelled simulations, the battery life effects of an RL algorithm are benchmarked against static and dynamic optimisation approaches, with the foundation laid for a hardware benchmark to follow. It is shown that using RL within a TinyML-enabled IoT system to optimise the system operations, including cloud anomaly processing and on-device training, yields an improved battery life of 22.86% and 10.86% compared to static and dynamic optimisation approaches respectively. The proposed solution can be deployed to resource-constrained hardware, given its low memory footprint of 800 B, which could be further reduced. This further facilitates the real-world deployment of such systems, including key sectors such as smart agriculture.
How well the heart is functioning can be quantified through measurements of myocardial deformation via echocardiography. Clinical assessment of cardiac function is generally focused on global indices of relative shortening, however, territorial, and segmental strain indices have shown to be abnormal in regions of myocardial disease, such as scar. In this work, we propose a single framework to predict myocardial disease substrates at global, territorial, and segmental levels using regional myocardial strain traces as input to a convolutional neural network (CNN)-based classification algorithm. An anatomically meaningful representation of the input data from the clinically standard bullseye representation to a multi-channel 2D image is proposed, to formulate the task as an image classification problem, thus enabling the use of state-of-the-art neural network configurations. A Fully Convolutional Network (FCN) is trained to detect and localize myocardial scar from regional left ventricular (LV) strain patterns. Simulated regional strain data from a controlled dataset of virtual patients with varying degrees and locations of myocardial scar is used for training and validation. The proposed method successfully detects and localizes the scars on 98% of the 5490 left ventricle (LV) segments of the 305 patients in the test set using strain traces only. Due to the sparse existence of scar, only 10% of the LV segments in the virtual patient cohort have scar. Taking the imbalance into account, the class balanced accuracy is calculated as 95%. The performance is reported on global, territorial, and segmental levels. The proposed method proves successful on the strain traces of the virtual cohort and offers the potential to solve the regional myocardial scar detection problem on the strain traces of the real patient cohorts.
Large-scale applications of Visual Place Recognition (VPR) require computationally efficient approaches. Further, a well-balanced combination of data-based and training-free approaches can decrease the required amount of training data and effort and can reduce the influence of distribution shifts between the training and application phases. This paper proposes a runtime and data-efficient hierarchical VPR pipeline that extends existing approaches and presents novel ideas. There are three main contributions: First, we propose Local Positional Graphs (LPG), a training-free and runtime-efficient approach to encode spatial context information of local image features. LPG can be combined with existing local feature detectors and descriptors and considerably improves the image-matching quality compared to existing techniques in our experiments. Second, we present Attentive Local SPED (ATLAS), an extension of our previous local features approach with an attention module that improves the feature quality while maintaining high data efficiency. The influence of the proposed modifications is evaluated in an extensive ablation study. Third, we present a hierarchical pipeline that exploits hyperdimensional computing to use the same local features as holistic HDC-descriptors for fast candidate selection and for candidate reranking. We combine all contributions in a runtime and data-efficient VPR pipeline that shows benefits over the state-of-the-art method Patch-NetVLAD on a large collection of standard place recognition datasets with 15$\%$ better performance in VPR accuracy, 54$\times$ faster feature comparison speed, and 55$\times$ less descriptor storage occupancy, making our method promising for real-world high-performance large-scale VPR in changing environments. Code will be made available with publication of this paper.
In this work, we show that synthetic data created by generative models is complementary to computer graphics (CG) rendered data for achieving remarkable generalization performance on diverse real-world scenes for 3D human pose and shape estimation (HPS). Specifically, we propose an effective approach based on recent diffusion models, termed HumanWild, which can effortlessly generate human images and corresponding 3D mesh annotations. We first collect a large-scale human-centric dataset with comprehensive annotations, e.g., text captions and surface normal images. Then, we train a customized ControlNet model upon this dataset to generate diverse human images and initial ground-truth labels. At the core of this step is that we can easily obtain numerous surface normal images from a 3D human parametric model, e.g., SMPL-X, by rendering the 3D mesh onto the image plane. As there exists inevitable noise in the initial labels, we then apply an off-the-shelf foundation segmentation model, i.e., SAM, to filter negative data samples. Our data generation pipeline is flexible and customizable to facilitate different real-world tasks, e.g., ego-centric scenes and perspective-distortion scenes. The generated dataset comprises 0.79M images with corresponding 3D annotations, covering versatile viewpoints, scenes, and human identities. We train various HPS regressors on top of the generated data and evaluate them on a wide range of benchmarks (3DPW, RICH, EgoBody, AGORA, SSP-3D) to verify the effectiveness of the generated data. By exclusively employing generative models, we generate large-scale in-the-wild human images and high-quality annotations, eliminating the need for real-world data collection.
Unique player identification is a fundamental module in vision-driven sports analytics. Identifying players from broadcast videos can aid with various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatic detection of jersey numbers using deep features is challenging primarily due to: a) motion blur, b) low resolution video feed, and c) occlusions. With their recent success in various vision tasks, masked autoencoders (MAEs) have emerged as a superior alternative to conventional feature extractors. However, most MAEs simply zero-out image patches either randomly or focus on where to mask rather than how to mask. Motivated by human vision, we devise a novel domain-guided masking policy for MAEs termed d-MAE to facilitate robust feature extraction in the presence of motion blur for player identification. We further introduce a new spatio-temporal network leveraging our novel d-MAE for unique player identification. We conduct experiments on three large-scale sports datasets, including a curated baseball dataset, the SoccerNet dataset, and an in-house ice hockey dataset. We preprocess the datasets using an upgraded keyframe identification (KfID) module by focusing on frames containing jersey numbers. Additionally, we propose a keyframe-fusion technique to augment keyframes, preserving spatial and temporal context. Our spatio-temporal network showcases significant improvements, surpassing the current state-of-the-art by 8.58%, 4.29%, and 1.20% in the test set accuracies, respectively. Rigorous ablations highlight the effectiveness of our domain-guided masking approach and the refined KfID module, resulting in performance enhancements of 1.48% and 1.84% respectively, compared to original architectures.
Text-to-3D synthesis has recently seen intriguing advances by combining the text-to-image models with 3D representation methods, e.g., Gaussian Splatting (GS), via Score Distillation Sampling (SDS). However, a hurdle of existing methods is the low efficiency, per-prompt optimization for a single 3D object. Therefore, it is imperative for a paradigm shift from per-prompt optimization to one-stage generation for any unseen text prompts, which yet remains challenging. A hurdle is how to directly generate a set of millions of 3D Gaussians to represent a 3D object. This paper presents BrightDreamer, an end-to-end single-stage approach that can achieve generalizable and fast (77 ms) text-to-3D generation. Our key idea is to formulate the generation process as estimating the 3D deformation from an anchor shape with predefined positions. For this, we first propose a Text-guided Shape Deformation (TSD) network to predict the deformed shape and its new positions, used as the centers (one attribute) of 3D Gaussians. To estimate the other four attributes (i.e., scaling, rotation, opacity, and SH coefficient), we then design a novel Text-guided Triplane Generator (TTG) to generate a triplane representation for a 3D object. The center of each Gaussian enables us to transform the triplane feature into the four attributes. The generated 3D Gaussians can be finally rendered at 705 frames per second. Extensive experiments demonstrate the superiority of our method over existing methods. Also, BrightDreamer possesses a strong semantic understanding capability even for complex text prompts. The project code is available at https://vlislab22.github.io/BrightDreamer.
Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques, notable progress has been achieved in video generation. However, existing methods build upon the spatiotemporal consistency assumptions between adjacent frames, which cannot be satisfied in the ego-to-exo scenarios due to drastic changes in views. To this end, this paper proposes an Intention-Driven Ego-to-exo video generation framework (IDE) that leverages action intention consisting of human movement and action description as view-independent representation to guide video generation, preserving the consistency of content and motion. Specifically, the egocentric head trajectory is first estimated through multi-view stereo matching. Then, cross-view feature perception module is introduced to establish correspondences between exo- and ego- views, guiding the trajectory transformation module to infer human full-body movement from the head trajectory. Meanwhile, we present an action description unit that maps the action semantics into the feature space consistent with the exocentric image. Finally, the inferred human movement and high-level action descriptions jointly guide the generation of exocentric motion and interaction content (i.e., corresponding optical flow and occlusion maps) in the backward process of the diffusion model, ultimately warping them into the corresponding exocentric video. We conduct extensive experiments on the relevant dataset with diverse exo-ego video pairs, and our IDE outperforms state-of-the-art models in both subjective and objective assessments, demonstrating its efficacy in ego-to-exo video generation.