ED-ViT: Splitting Vision Transformer for Distributed Inference on Edge Devices

Deep learning models are increasingly deployed on resource-constrained edge devices for real-time data analytics. In recent years, Vision Transformer models and their variants have demonstrated outstanding performance across various computer vision tasks. However, their high computational demands and inference latency pose significant challenges for model deployment on resource-constraint edge devices. To address this issue, we propose a novel Vision Transformer splitting framework, ED-ViT, designed to execute complex models across multiple edge devices efficiently. Specifically, we partition Vision Transformer models into several sub-models, where each sub-model is tailored to handle a specific subset of data classes. To further minimize computation overhead and inference latency, we introduce a class-wise pruning technique that reduces the size of each sub-model. We conduct extensive experiments on five datasets with three model structures, demonstrating that our approach significantly reduces inference latency on edge devices and achieves a model size reduction of up to 28.9 times and 34.1 times, respectively, while maintaining test accuracy comparable to the original Vision Transformer. Additionally, we compare ED-ViT with two state-of-the-art methods that deploy CNN and SNN models on edge devices, evaluating accuracy, inference time, and overall model size. Our comprehensive evaluation underscores the effectiveness of the proposed ED-ViT framework.

Gaussian Representation for Deformable Image Registration

Deformable image registration (DIR) is a fundamental task in radiotherapy, with existing methods often struggling to balance computational efficiency, registration accuracy, and speed effectively. We introduce a novel DIR approach employing parametric 3D Gaussian control points achieving a better tradeoff. It provides an explicit and flexible representation for spatial deformation fields between 3D volumetric medical images, producing a displacement vector field (DVF) across all volumetric positions. The movement of individual voxels is derived using linear blend skinning (LBS) through localized interpolation of transformations associated with neighboring Gaussians. This interpolation strategy not only simplifies the determination of voxel motions but also acts as an effective regularization technique. Our approach incorporates a unified optimization process through backpropagation, enabling iterative learning of both the parameters of the 3D Gaussians and their transformations. Additionally, the density of Gaussians is adjusted adaptively during the learning phase to accommodate varying degrees of motion complexity. We validated our approach on the 4D-CT lung DIR-Lab and cardiac ACDC datasets, achieving an average target registration error (TRE) of 1.06 mm within a much-improved processing time of 2.43 seconds for the DIR-Lab dataset over existing methods, demonstrating significant advancements in both accuracy and efficiency.

TAMBRIDGE: Bridging Frame-Centered Tracking and 3D Gaussian Splatting for Enhanced SLAM

The limited robustness of 3D Gaussian Splatting (3DGS) to motion blur and camera noise, along with its poor real-time performance, restricts its application in robotic SLAM tasks. Upon analysis, the primary causes of these issues are the density of views with motion blur and the cumulative errors in dense pose estimation from calculating losses based on noisy original images and rendering results, which increase the difficulty of 3DGS rendering convergence. Thus, a cutting-edge 3DGS-based SLAM system is introduced, leveraging the efficiency and flexibility of 3DGS to achieve real-time performance while remaining robust against sensor noise, motion blur, and the challenges posed by long-session SLAM. Central to this approach is the Fusion Bridge module, which seamlessly integrates tracking-centered ORB Visual Odometry with mapping-centered online 3DGS. Precise pose initialization is enabled by this module through joint optimization of re-projection and rendering loss, as well as strategic view selection, enhancing rendering convergence in large-scale scenes. Extensive experiments demonstrate state-of-the-art rendering quality and localization accuracy, positioning this system as a promising solution for real-world robotics applications that require stable, near-real-time performance. Our project is available at https://ZeldaFromHeaven.github.io/TAMBRIDGE/

CPT-Interp: Continuous sPatial and Temporal Motion Modeling for 4D Medical Image Interpolation

Motion information from 4D medical imaging offers critical insights into dynamic changes in patient anatomy for clinical assessments and radiotherapy planning and, thereby, enhances the capabilities of 3D image analysis. However, inherent physical and technical constraints of imaging hardware often necessitate a compromise between temporal resolution and image quality. Frame interpolation emerges as a pivotal solution to this challenge. Previous methods often suffer from discretion when they estimate the intermediate motion and execute the forward warping. In this study, we draw inspiration from fluid mechanics to propose a novel approach for continuously modeling patient anatomic motion using implicit neural representation. It ensures both spatial and temporal continuity, effectively bridging Eulerian and Lagrangian specifications together to naturally facilitate continuous frame interpolation. Our experiments across multiple datasets underscore the method's superior accuracy and speed. Furthermore, as a case-specific optimization (training-free) approach, it circumvents the need for extensive datasets and addresses model generalization issues.

Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods

Background and purpose: Deformable image registration (DIR) is a crucial tool in radiotherapy for extracting and modelling organ motion. However, when significant changes and sliding boundaries are present, it faces compromised accuracy and uncertainty, determining the subsequential contour propagation and dose accumulation procedures. Materials and methods: We propose an implicit neural representation (INR)-based approach modelling motion continuously in both space and time, named Continues-sPatial-Temporal DIR (CPT-DIR). This method uses a multilayer perception (MLP) network to map 3D coordinate (x,y,z) to its corresponding velocity vector (vx,vy,vz). The displacement vectors (dx,dy,dz) are then calculated by integrating velocity vectors over time. The MLP's parameters can rapidly adapt to new cases without pre-training, enhancing optimisation. The DIR's performance was tested on the DIR-Lab dataset of 10 lung 4DCT cases, using metrics of landmark accuracy (TRE), contour conformity (Dice) and image similarity (MAE). Results: The proposed CPT-DIR can reduce landmark TRE from 2.79mm to 0.99mm, outperforming B-splines' results for all cases. The MAE of the whole-body region improves from 35.46HU to 28.99HU. Furthermore, CPT-DIR surpasses B-splines for accuracy in the sliding boundary region, lowering MAE and increasing Dice coefficients for the ribcage from 65.65HU and 90.41% to 42.04HU and 90.56%, versus 75.40HU and 89.30% without registration. Meanwhile, CPT-DIR offers significant speed advantages, completing in under 15 seconds compared to a few minutes with the conventional B-splines method. Conclusion: Leveraging the continuous representations, the CPT-DIR method significantly enhances registration accuracy, automation and speed, outperforming traditional B-splines in landmark and contour precision, particularly in the challenging areas.

UVMap-ID: A Controllable and Personalized UV Map Generative Model

Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D text-to-image diffusion models into the 3D domain for generating human textures (UV Maps). However, some important problems about UV Map Generative models are still not solved, i.e., how to generate personalized texture maps for any given face image, and how to define and evaluate the quality of these generated texture maps. To solve the above problems, we introduce a novel method, UVMap-ID, which is a controllable and personalized UV Map generative model. Unlike traditional large-scale training methods in 2D, we propose to fine-tune a pre-trained text-to-image diffusion model which is integrated with a face fusion module for achieving ID-driven customized generation. To support the finetuning strategy, we introduce a small-scale attribute-balanced training dataset, including high-quality textures with labeled text and Face ID. Additionally, we introduce some metrics to evaluate the multiple aspects of the textures. Finally, both quantitative and qualitative analyses demonstrate the effectiveness of our method in controllable and personalized UV Map generation. Code is publicly available via https://github.com/twowwj/UVMap-ID.

Point-In-Context: Understanding Point Cloud via In-Context Learning

With the emergence of large-scale models trained on diverse datasets, in-context learning has emerged as a promising paradigm for multitasking, notably in natural language processing and image processing. However, its application in 3D point cloud tasks remains largely unexplored. In this work, we introduce Point-In-Context (PIC), a novel framework for 3D point cloud understanding via in-context learning. We address the technical challenge of effectively extending masked point modeling to 3D point clouds by introducing a Joint Sampling module and proposing a vanilla version of PIC called Point-In-Context-Generalist (PIC-G). PIC-G is designed as a generalist model for various 3D point cloud tasks, with inputs and outputs modeled as coordinates. In this paradigm, the challenging segmentation task is achieved by assigning label points with XYZ coordinates for each category; the final prediction is then chosen based on the label point closest to the predictions. To break the limitation by the fixed label-coordinate assignment, which has poor generalization upon novel classes, we propose two novel training strategies, In-Context Labeling and In-Context Enhancing, forming an extended version of PIC named Point-In-Context-Segmenter (PIC-S), targeting improving dynamic context labeling and model training. By utilizing dynamic in-context labels and extra in-context pairs, PIC-S achieves enhanced performance and generalization capability in and across part segmentation datasets. PIC is a general framework so that other tasks or datasets can be seamlessly introduced into our PIC through a unified data format. We conduct extensive experiments to validate the versatility and adaptability of our proposed methods in handling a wide range of tasks and segmenting multi-datasets. Our PIC-S is capable of generalizing unseen datasets and performing novel part segmentation by customizing prompts.

Diffusion Schrödinger Bridge Models for High-Quality MR-to-CT Synthesis for Head and Neck Proton Treatment Planning

In recent advancements in proton therapy, MR-based treatment planning is gaining momentum to minimize additional radiation exposure compared to traditional CT-based methods. This transition highlights the critical need for accurate MR-to-CT image synthesis, which is essential for precise proton dose calculations. Our research introduces the Diffusion Schr\"odinger Bridge Models (DSBM), an innovative approach for high-quality MR-to-CT synthesis. DSBM learns the nonlinear diffusion processes between MR and CT data distributions. This method improves upon traditional diffusion models by initiating synthesis from the prior distribution rather than the Gaussian distribution, enhancing both generation quality and efficiency. We validated the effectiveness of DSBM on a head and neck cancer dataset, demonstrating its superiority over traditional image synthesis methods through both image-level and dosimetric-level evaluations. The effectiveness of DSBM in MR-based proton treatment planning highlights its potential as a valuable tool in various clinical scenarios.

VG4D: Vision-Language Model Goes 4D Video Recognition

Understanding the real world through point cloud video is a crucial aspect of robotics and autonomous driving systems. However, prevailing methods for 4D point cloud recognition have limitations due to sensor resolution, which leads to a lack of detailed information. Recent advances have shown that Vision-Language Models (VLM) pre-trained on web-scale text-image datasets can learn fine-grained visual concepts that can be transferred to various downstream tasks. However, effectively integrating VLM into the domain of 4D point clouds remains an unresolved problem. In this work, we propose the Vision-Language Models Goes 4D (VG4D) framework to transfer VLM knowledge from visual-text pre-trained models to a 4D point cloud network. Our approach involves aligning the 4D encoder's representation with a VLM to learn a shared visual and text space from training on large-scale image-text pairs. By transferring the knowledge of the VLM to the 4D encoder and combining the VLM, our VG4D achieves improved recognition performance. To enhance the 4D encoder, we modernize the classic dynamic point cloud backbone and propose an improved version of PSTNet, im-PSTNet, which can efficiently model point cloud videos. Experiments demonstrate that our method achieves state-of-the-art performance for action recognition on both the NTU RGB+D 60 dataset and the NTU RGB+D 120 dataset. Code is available at \url{https://github.com/Shark0-0/VG4D}.

Neural Clustering based Visual Representation Learning

We investigate a fundamental aspect of machine vision: the measurement of features, by revisiting clustering, one of the most classic approaches in machine learning and data analysis. Existing visual feature extractors, including ConvNets, ViTs, and MLPs, represent an image as rectangular regions. Though prevalent, such a grid-style paradigm is built upon engineering practice and lacks explicit modeling of data distribution. In this work, we propose feature extraction with clustering (FEC), a conceptually elegant yet surprisingly ad-hoc interpretable neural clustering framework, which views feature extraction as a process of selecting representatives from data and thus automatically captures the underlying data distribution. Given an image, FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives. Such an iterative working mechanism is implemented in the form of several neural layers and the final representatives can be used for downstream tasks. The cluster assignments across layers, which can be viewed and inspected by humans, make the forward process of FEC fully transparent and empower it with promising ad-hoc interpretability. Extensive experiments on various visual recognition models and tasks verify the effectiveness, generality, and interpretability of FEC. We expect this work will provoke a rethink of the current de facto grid-style paradigm.