Related papers: Structure-Adaptive Sparse Diffusion in Voxel Space…

Stereo-LiDAR fusion is a promising task in that we can utilize two different types of 3D perceptions for practical usage -- dense 3D information (stereo cameras) and highly-accurate sparse point clouds (LiDAR). However, due to their…

The safe operation of automated vehicles depends on their ability to perceive the environment comprehensively. However, occlusion, sensor range, and environmental factors limit their perception capabilities. To overcome these limitations,…

While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency.…

The performance of medical image analysis systems is constrained by the quantity of high-quality image annotations. Such systems require data to be annotated by experts with years of training, especially when diagnostic decisions are…

Automated cell segmentation in microscopy images is essential for biomedical research, yet conventional methods are labor-intensive and prone to error. While deep learning-based approaches have proven effective, they often require large…

Spatial control methods using additional modules on pretrained diffusion models have gained attention for enabling conditional generation in natural images. These methods guide the generation process with new conditions while leveraging the…

Existing methods for human parsing into body parts and clothing often use fixed mask categories with broad labels that obscure fine-grained clothing types. Recent open-vocabulary segmentation approaches leverage pretrained text-to-image…

Diffusion models have emerged as powerful tools for 3D medical image generation, yet bridging the gap between standard training objectives and clinical relevance remains a challenge. This paper presents a method to enhance 3D diffusion…

This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the…

INTRODUCTION | Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation, forcing reliance on sparse 2D slices. Weakly supervised Sparse-to-Dense frameworks bridge this gap,…

Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels…

Quantitative cancer image analysis relies on the accurate delineation of tumours, a very specialised and time-consuming task. For this reason, methods for automated segmentation of tumours in medical imaging have been extensively developed…

We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework, we observe that the underlying geometric structure is established during the early…

Currently prevalent multimodal 3D detection methods are built upon LiDAR-based detectors that usually use dense Bird's-Eye-View (BEV) feature maps. However, the cost of such BEV feature maps is quadratic to the detection range, making it…

Deformable tracking and real-time estimation of 3D tissue motion is essential to enable automation and image guidance applications in robotically assisted surgery. Our model, Sparse Efficient Neural Depth and Deformation (SENDD), extends…

This study introduces a novel point-wise diffusion model that processes spatio-temporal points independently to efficiently predict complex physical systems with shape variations. This methodological contribution lies in applying forward…

Neural representations (NRs), such as neural fields and 3D Gaussians, effectively model volumetric data in computed tomography (CT) but suffer from severe artifacts under sparse-view settings. To address this, we propose DiffNR, a novel…

Accurate medical image segmentation is fundamental to precision medicine, yet robust delineation remains challenging under heterogeneous appearances, ambiguous boundaries, and large anatomical variability. Similar intensity and texture…

LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the features of a single central voxel as an object proxy, or treat…

Inspired by recent findings that generative diffusion models learn semantically meaningful representations, we use them to discover the intrinsic hierarchical structure in biomedical 3D images using unsupervised segmentation. We show that…