Centre for Medical Image Computing, Department of Computer Science, University College London, UK
Abstract:Creating 3D content from single-view images is a challenging problem that has attracted considerable attention in recent years. Current approaches typically utilize score distillation sampling (SDS) from pre-trained 2D diffusion models to generate multi-view 3D representations. Although some methods have made notable progress by balancing generation speed and model quality, their performance is often limited by the visual inconsistencies of the diffusion model outputs. In this work, we propose ContrastiveGaussian, which integrates contrastive learning into the generative process. By using a perceptual loss, we effectively differentiate between positive and negative samples, leveraging the visual inconsistencies to improve 3D generation quality. To further enhance sample differentiation and improve contrastive learning, we incorporate a super-resolution model and introduce another Quantity-Aware Triplet Loss to address varying sample distributions during training. Our experiments demonstrate that our approach achieves superior texture fidelity and improved geometric consistency.
Abstract:Robust grasping of various objects from single-view perception is fundamental for dexterous robots. Previous works often rely on fully observable objects, expert demonstrations, or static grasping poses, which restrict their generalization ability and adaptability to external disturbances. In this paper, we present a reinforcement-learning-based framework that enables zero-shot dynamic dexterous grasping of a wide range of unseen objects from single-view perception, while performing adaptive motions to external disturbances. We utilize a hand-centric object representation for shape feature extraction that emphasizes interaction-relevant local shapes, enhancing robustness to shape variance and uncertainty. To enable effective hand adaptation to disturbances with limited observations, we propose a mixed curriculum learning strategy, which first utilizes imitation learning to distill a policy trained with privileged real-time visual-tactile feedback, and gradually transfers to reinforcement learning to learn adaptive motions under disturbances caused by observation noises and dynamic randomization. Our experiments demonstrate strong generalization in grasping unseen objects with random poses, achieving success rates of 97.0% across 247,786 simulated objects and 94.6% across 512 real objects. We also demonstrate the robustness of our method to various disturbances, including unobserved object movement and external forces, through both quantitative and qualitative evaluations. Project Page: https://zdchan.github.io/Robust_DexGrasp/
Abstract:Transformer-based architectures have revolutionized the landscape of deep learning. In computer vision domain, Vision Transformer demonstrates remarkable performance on par with or even surpassing that of convolutional neural networks. However, the quadratic computational complexity of its self-attention mechanism poses challenges for classical computing, making model training with high-dimensional input data, e.g., images, particularly expensive. To address such limitations, we propose a Hybrid Quantum Vision Transformer (HQViT), that leverages the principles of quantum computing to accelerate model training while enhancing model performance. HQViT introduces whole-image processing with amplitude encoding to better preserve global image information without additional positional encoding. By leveraging quantum computation on the most critical steps and selectively handling other components in a classical way, we lower the cost of quantum resources for HQViT. The qubit requirement is minimized to $O(log_2N)$ and the number of parameterized quantum gates is only $O(log_2d)$, making it well-suited for Noisy Intermediate-Scale Quantum devices. By offloading the computationally intensive attention coefficient matrix calculation to the quantum framework, HQViT reduces the classical computational load by $O(T^2d)$. Extensive experiments across various computer vision datasets demonstrate that HQViT outperforms existing models, achieving a maximum improvement of up to $10.9\%$ (on the MNIST 10-classification task) over the state of the art. This work highlights the great potential to combine quantum and classical computing to cope with complex image classification tasks.
Abstract:Lung cancer is a leading cause of cancer-related deaths globally. PET-CT is crucial for imaging lung tumors, providing essential metabolic and anatomical information, while it faces challenges such as poor image quality, motion artifacts, and complex tumor morphology. Deep learning-based models are expected to address these problems, however, existing small-scale and private datasets limit significant performance improvements for these methods. Hence, we introduce a large-scale PET-CT lung tumor segmentation dataset, termed PCLT20K, which comprises 21,930 pairs of PET-CT images from 605 patients. Furthermore, we propose a cross-modal interactive perception network with Mamba (CIPA) for lung tumor segmentation in PET-CT images. Specifically, we design a channel-wise rectification module (CRM) that implements a channel state space block across multi-modal features to learn correlated representations and helps filter out modality-specific noise. A dynamic cross-modality interaction module (DCIM) is designed to effectively integrate position and context information, which employs PET images to learn regional position information and serves as a bridge to assist in modeling the relationships between local features of CT images. Extensive experiments on a comprehensive benchmark demonstrate the effectiveness of our CIPA compared to the current state-of-the-art segmentation methods. We hope our research can provide more exploration opportunities for medical image segmentation. The dataset and code are available at https://github.com/mj129/CIPA.
Abstract:Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to enable precise object motion control through explicitly defined spatial paths. However, existing methods struggle with complex object movements and multi-object motion control, resulting in imprecise trajectory adherence, poor object consistency, and compromised visual quality. Furthermore, these methods only support trajectory control in a single format, limiting their applicability in diverse scenarios. Additionally, there is no publicly available dataset or benchmark specifically tailored for trajectory-controllable video generation, hindering robust training and systematic evaluation. To address these challenges, we introduce MagicMotion, a novel image-to-video generation framework that enables trajectory control through three levels of conditions from dense to sparse: masks, bounding boxes, and sparse boxes. Given an input image and trajectories, MagicMotion seamlessly animates objects along defined trajectories while maintaining object consistency and visual quality. Furthermore, we present MagicData, a large-scale trajectory-controlled video dataset, along with an automated pipeline for annotation and filtering. We also introduce MagicBench, a comprehensive benchmark that assesses both video quality and trajectory control accuracy across different numbers of objects. Extensive experiments demonstrate that MagicMotion outperforms previous methods across various metrics. Our project page are publicly available at https://quanhaol.github.io/magicmotion-site.
Abstract:Diffusion models have demonstrated impressive generation capabilities, particularly with recent advancements leveraging transformer architectures to improve both visual and artistic quality. However, Diffusion Transformers (DiTs) continue to encounter challenges related to low inference speed, primarily due to the iterative denoising process. To address this issue, we propose BlockDance, a training-free approach that explores feature similarities at adjacent time steps to accelerate DiTs. Unlike previous feature-reuse methods that lack tailored reuse strategies for features at different scales, BlockDance prioritizes the identification of the most structurally similar features, referred to as Structurally Similar Spatio-Temporal (STSS) features. These features are primarily located within the structure-focused blocks of the transformer during the later stages of denoising. BlockDance caches and reuses these highly similar features to mitigate redundant computation, thereby accelerating DiTs while maximizing consistency with the generated results of the original model. Furthermore, considering the diversity of generated content and the varying distributions of redundant features, we introduce BlockDance-Ada, a lightweight decision-making network tailored for instance-specific acceleration. BlockDance-Ada dynamically allocates resources and provides superior content quality. Both BlockDance and BlockDance-Ada have proven effective across various generation tasks and models, achieving accelerations between 25% and 50% while maintaining generation quality.
Abstract:Automatically adapting novels into screenplays is important for the TV, film, or opera industries to promote products with low costs. The strong performances of large language models (LLMs) in long-text generation call us to propose a LLM based framework Reader-Rewriter (R$^2$) for this task. However, there are two fundamental challenges here. First, the LLM hallucinations may cause inconsistent plot extraction and screenplay generation. Second, the causality-embedded plot lines should be effectively extracted for coherent rewriting. Therefore, two corresponding tactics are proposed: 1) A hallucination-aware refinement method (HAR) to iteratively discover and eliminate the affections of hallucinations; and 2) a causal plot-graph construction method (CPC) based on a greedy cycle-breaking algorithm to efficiently construct plot lines with event causalities. Recruiting those efficient techniques, R$^2$ utilizes two modules to mimic the human screenplay rewriting process: The Reader module adopts a sliding window and CPC to build the causal plot graphs, while the Rewriter module generates first the scene outlines based on the graphs and then the screenplays. HAR is integrated into both modules for accurate inferences of LLMs. Experimental results demonstrate the superiority of R$^2$, which substantially outperforms three existing approaches (51.3%, 22.6%, and 57.1% absolute increases) in pairwise comparison at the overall win rate for GPT-4o.
Abstract:This paper presents NimbleReg, a light-weight deep-learning (DL) framework for diffeomorphic image registration leveraging surface representation of multiple segmented anatomical regions. Deep learning has revolutionized image registration but most methods typically rely on cumbersome gridded representations, leading to hardware-intensive models. Reliable fine-grained segmentations, that are now accessible at low cost, are often used to guide the alignment. Light-weight methods representing segmentations in terms of boundary surfaces have been proposed, but they lack mechanism to support the fusion of multiple regional mappings into an overall diffeomorphic transformation. Building on these advances, we propose a DL registration method capable of aligning surfaces from multiple segmented regions to generate an overall diffeomorphic transformation for the whole ambient space. The proposed model is light-weight thanks to a PointNet backbone. Diffeomoprhic properties are guaranteed by taking advantage of the stationary velocity field parametrization of diffeomorphisms. We demonstrate that this approach achieves alignment comparable to state-of-the-art DL-based registration techniques that consume images.
Abstract:Monocular visual localization plays a pivotal role in advanced driver assistance systems and autonomous driving by estimating a vehicle's ego-motion from a single pinhole camera. Nevertheless, conventional monocular visual odometry encoun-ters challenges in scale estimation due to the absence of depth information during projection. Previous methodologies, whether rooted in physical constraints or deep learning paradigms, con-tend with issues related to computational complexity and the management of dynamic objects. This study extends our prior research, presenting innovative strategies for ego-motion estima-tion and the selection of ground points. Striving for a nuanced equilibrium between computational efficiency and precision, we propose a hybrid method that leverages the SegNeXt model for real-time applications, encompassing both ego-motion estimation and ground point selection. Our methodology incorporates dy-namic object masks to eliminate unstable features and employs ground plane masks for meticulous triangulation. Furthermore, we exploit Geometry-constraint to delineate road regions for scale recovery. The integration of this approach with the mo-nocular version of ORB-SLAM3 culminates in the accurate esti-mation of a road model, a pivotal component in our scale recov-ery process. Rigorous experiments, conducted on the KITTI da-taset, systematically compare our method with existing monocu-lar visual odometry algorithms and contemporary scale recovery methodologies. The results undeniably confirm the superior ef-fectiveness of our approach, surpassing state-of-the-art visual odometry algorithms. Our source code is available at https://git hub.com/bFr0zNq/MVOSegScale.
Abstract:Accurate segmentation of 3D vascular structures is essential for various medical imaging applications. The dispersed nature of vascular structures leads to inherent spatial uncertainty and necessitates location awareness, yet most current 3D medical segmentation models rely on the patch-wise training strategy that usually loses this spatial context. In this study, we introduce the Coordinate-aware Modulated Mamba Network (COMMA) and contribute a manually labeled dataset of 570 cases, the largest publicly available 3D vessel dataset to date. COMMA leverages both entire and cropped patch data through global and local branches, ensuring robust and efficient spatial location awareness. Specifically, COMMA employs a channel-compressed Mamba (ccMamba) block to encode entire image data, capturing long-range dependencies while optimizing computational costs. Additionally, we propose a coordinate-aware modulated (CaM) block to enhance interactions between the global and local branches, allowing the local branch to better perceive spatial information. We evaluate COMMA on six datasets, covering two imaging modalities and five types of vascular tissues. The results demonstrate COMMA's superior performance compared to state-of-the-art methods with computational efficiency, especially in segmenting small vessels. Ablation studies further highlight the importance of our proposed modules and spatial information. The code and data will be open source at https://github.com/shigen-StoneRoot/COMMA.