Abstract:This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs). Scene-LLM adopts a hybrid 3D visual feature representation, that incorporates dense spatial information and supports scene state updates. The model employs a projection layer to efficiently project these features in the pre-trained textual embedding space, enabling effective interpretation of 3D visual information. Unique to our approach is the integration of both scene-level and ego-centric 3D information. This combination is pivotal for interactive planning, where scene-level data supports global planning and ego-centric data is important for localization. Notably, we use ego-centric 3D frame features for feature alignment, an efficient technique that enhances the model's ability to align features of small objects within the scene. Our experiments with Scene-LLM demonstrate its strong capabilities in dense captioning, question answering, and interactive planning. We believe Scene-LLM advances the field of 3D visual understanding and reasoning, offering new possibilities for sophisticated agent interactions in indoor settings.
Abstract:In the financial services industry, forecasting the risk factor distribution conditional on the history and the current market environment is the key to market risk modeling in general and value at risk (VaR) model in particular. As one of the most widely adopted VaR models in commercial banks, Historical simulation (HS) uses the empirical distribution of daily returns in a historical window as the forecast distribution of risk factor returns in the next day. The objectives for financial time series generation are to generate synthetic data paths with good variety, and similar distribution and dynamics to the original historical data. In this paper, we apply multiple existing deep generative methods (e.g., CGAN, CWGAN, Diffusion, and Signature WGAN) for conditional time series generation, and propose and test two new methods for conditional multi-step time series generation, namely Encoder-Decoder CGAN and Conditional TimeVAE. Furthermore, we introduce a comprehensive framework with a set of KPIs to measure the quality of the generated time series for financial modeling. The KPIs cover distribution distance, autocorrelation and backtesting. All models (HS, parametric and neural networks) are tested on both historical USD yield curve data and additional data simulated from GARCH and CIR processes. The study shows that top performing models are HS, GARCH and CWGAN models. Future research directions in this area are also discussed.
Abstract:We introduce AnyHome, a framework that translates open-vocabulary descriptions, ranging from simple labels to elaborate paragraphs, into well-structured and textured 3D indoor scenes at a house-scale. Inspired by cognition theories, AnyHome employs an amodal structured representation to capture 3D spatial cues from textual narratives and then uses egocentric inpainting to enrich these scenes. To this end, we begin by using specially designed template prompts for Large Language Models (LLMs), which enable precise control over the textual input. We then utilize intermediate representations to maintain the spatial structure's consistency, ensuring that the 3D scenes align closely with the textual description. Then, we apply a Score Distillation Sampling process to refine the placement of objects. Lastly, an egocentric inpainting process is incorporated to enhance the realism and appearance of the scenes. AnyHome stands out due to its hierarchical structured representation combined with the versatility of open-vocabulary text interpretation. This allows for extensive customization of indoor scenes at various levels of granularity. We demonstrate that AnyHome can reliably generate a range of diverse indoor scenes, characterized by their detailed spatial structures and textures, all corresponding to the free-form textual inputs.
Abstract:A generative model for high-fidelity point clouds is of great importance in synthesizing 3d environments for applications such as autonomous driving and robotics. Despite the recent success of deep generative models for 2d images, it is non-trivial to generate 3d point clouds without a comprehensive understanding of both local and global geometric structures. In this paper, we devise a new 3d point cloud generation framework using a divide-and-conquer approach, where the whole generation process can be divided into a set of patch-wise generation tasks. Specifically, all patch generators are based on learnable priors, which aim to capture the information of geometry primitives. We introduce point- and patch-wise transformers to enable the interactions between points and patches. Therefore, the proposed divide-and-conquer approach contributes to a new understanding of point cloud generation from the geometry constitution of 3d shapes. Experimental results on a variety of object categories from the most popular point cloud dataset, ShapeNet, show the effectiveness of the proposed patch-wise point cloud generation, where it clearly outperforms recent state-of-the-art methods for high-fidelity point cloud generation.
Abstract:This paper proposes BPNet, a novel end-to-end deep learning framework to learn B\'ezier primitive segmentation on 3D point clouds. The existing works treat different primitive types separately, thus limiting them to finite shape categories. To address this issue, we seek a generalized primitive segmentation on point clouds. Taking inspiration from B\'ezier decomposition on NURBS models, we transfer it to guide point cloud segmentation casting off primitive types. A joint optimization framework is proposed to learn B\'ezier primitive segmentation and geometric fitting simultaneously on a cascaded architecture. Specifically, we introduce a soft voting regularizer to improve primitive segmentation and propose an auto-weight embedding module to cluster point features, making the network more robust and generic. We also introduce a reconstruction module where we successfully process multiple CAD models with different primitives simultaneously. We conducted extensive experiments on the synthetic ABC dataset and real-scan datasets to validate and compare our approach with different baseline methods. Experiments show superior performance over previous work in terms of segmentation, with a substantially faster inference speed.
Abstract:The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation. Thanks to its impressive capabilities in all-round segmentation tasks and its prompt-based interface, SAM has sparked intensive discussion within the community. It is even said by many prestigious experts that image segmentation task has been "finished" by SAM. However, medical image segmentation, although an important branch of the image segmentation family, seems not to be included in the scope of Segmenting "Anything". Many individual experiments and recent studies have shown that SAM performs subpar in medical image segmentation. A natural question is how to find the missing piece of the puzzle to extend the strong segmentation capability of SAM to medical image segmentation. In this paper, instead of fine-tuning the SAM model, we propose Med SAM Adapter, which integrates the medical specific domain knowledge to the segmentation model, by a simple yet effective adaptation technique. Although this work is still one of a few to transfer the popular NLP technique Adapter to computer vision cases, this simple implementation shows surprisingly good performance on medical image segmentation. A medical image adapted SAM, which we have dubbed Medical SAM Adapter (MSA), shows superior performance on 19 medical image segmentation tasks with various image modalities including CT, MRI, ultrasound image, fundus image, and dermoscopic images. MSA outperforms a wide range of state-of-the-art (SOTA) medical image segmentation methods, such as nnUNet, TransUNet, UNetr, MedSegDiff, and also outperforms the fully fine-turned MedSAM with a considerable performance gap. Code will be released at: https://github.com/WuJunde/Medical-SAM-Adapter.
Abstract:This paper presents a novel method for efficiently solving trajectory planning problems for swarm robotics in cluttered environments. While recent research has demonstrated high success rates in real-time local trajectory planning for swarm robotics in cluttered environments, optimizing every trajectory for each robot is computationally expensive, with a computational complexity of $O\left(n^2\right)$ to $ O\left(n^3\right)$. To address this issue, we first propose the concept of the \emph{optimal virtual tube}, which includes infinite optimal trajectories. Under certain conditions, any optimal trajectory in the optimal virtual tube can be expressed as a convex combination of a finite number of optimal trajectories, with a computational complexity of $O\left(1\right)$. Afterward, a planning method of \emph{the optimal virtual tube} is proposed. In simulations and experiments, we show that the proposed method efficiently reduces calculation and is validated by comparison with traditional methods.
Abstract:Language is one of the primary means by which we describe the 3D world around us. While rapid progress has been made in text-to-2D-image synthesis, similar progress in text-to-3D-shape synthesis has been hindered by the lack of paired (text, shape) data. Moreover, extant methods for text-to-shape generation have limited shape diversity and fidelity. We introduce TextCraft, a method to address these limitations by producing high-fidelity and diverse 3D shapes without the need for (text, shape) pairs for training. TextCraft achieves this by using CLIP and using a multi-resolution approach by first generating in a low-dimensional latent space and then upscaling to a higher resolution, improving the fidelity of the generated shape. To improve shape diversity, we use a discrete latent space which is modelled using a bidirectional transformer conditioned on the interchangeable image-text embedding space induced by CLIP. Moreover, we present a novel variant of classifier-free guidance, which further improves the accuracy-diversity trade-off. Finally, we perform extensive experiments that demonstrate that TextCraft outperforms state-of-the-art baselines.
Abstract:Open checkout-free grocery is the grocery store where the customers never have to wait in line to check out. Developing a system like this is not trivial since it faces challenges of recognizing the dynamic and massive flow of people. In particular, a clustering method that can efficiently assign each snapshot to the corresponding customer is essential for the system. In order to address the unique challenges in the open checkout-free grocery, we propose an efficient and effective person clustering method. Specifically, we first propose a Crowded Sub-Graph (CSG) to localize the relationship among massive and continuous data streams. CSG is constructed by the proposed Pick-Link-Weight (PLW) strategy, which \textbf{picks} the nodes based on time-space information, \textbf{links} the nodes via trajectory information, and \textbf{weighs} the links by the proposed von Mises-Fisher (vMF) similarity metric. Then, to ensure that the method adapts to the dynamic and unseen person flow, we propose Graph Convolutional Network (GCN) with a simple Nearest Neighbor (NN) strategy to accurately cluster the instances of CSG. GCN is adopted to project the features into low-dimensional separable space, and NN is able to quickly produce a result in this space upon dynamic person flow. The experimental results show that the proposed method outperforms other alternative algorithms in this scenario. In practice, the whole system has been implemented and deployed in several real-world open checkout-free groceries.
Abstract:We present ShapeCrafter, a neural network for recursive text-conditioned 3D shape generation. Existing methods to generate text-conditioned 3D shapes consume an entire text prompt to generate a 3D shape in a single step. However, humans tend to describe shapes recursively-we may start with an initial description and progressively add details based on intermediate results. To capture this recursive process, we introduce a method to generate a 3D shape distribution, conditioned on an initial phrase, that gradually evolves as more phrases are added. Since existing datasets are insufficient for training this approach, we present Text2Shape++, a large dataset of 369K shape-text pairs that supports recursive shape generation. To capture local details that are often used to refine shape descriptions, we build on top of vector-quantized deep implicit functions that generate a distribution of high-quality shapes. Results show that our method can generate shapes consistent with text descriptions, and shapes evolve gradually as more phrases are added. Our method supports shape editing, extrapolation, and can enable new applications in human-machine collaboration for creative design.