SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds

Transformers have been seldom employed in point cloud roof plane instance segmentation, which is the focus of this study, and existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints. To address this challenge, we establish two criteria that high-quality superpoints for Transformers should satisfy and introduce a corresponding two-stage superpoint generation process. The superpoints generated by our method not only have accurate boundaries, but also exhibit consistent geometric sizes and shapes, both of which greatly benefit the feature learning of superpoint Transformers. To compensate for the limitations of deep learning features when the training set size is limited, we incorporate multidimensional handcrafted features into the model. Additionally, we design a decoder that combines a Kolmogorov-Arnold Network with a Transformer module to improve instance prediction and mask extraction. Finally, our network's predictions are refined using traditional algorithm-based postprocessing. For evaluation, we annotated a real-world dataset and corrected annotation errors in the existing RoofN3D dataset. Experimental results show that our method achieves state-of-the-art performance on our dataset, as well as both the original and reannotated RoofN3D datasets. Moreover, our model is not sensitive to plane boundary annotations during training, significantly reducing the annotation burden. Through comprehensive experiments, we also identified key factors influencing roof plane segmentation performance: in addition to roof types, variations in point cloud density, density uniformity, and 3D point precision have a considerable impact. These findings underscore the importance of incorporating data augmentation strategies that account for point cloud quality to enhance model robustness under diverse and challenging conditions.

Pose-free 3D Gaussian splatting via shape-ray estimation

While generalizable 3D Gaussian splatting enables efficient, high-quality rendering of unseen scenes, it heavily depends on precise camera poses for accurate geometry. In real-world scenarios, obtaining accurate poses is challenging, leading to noisy pose estimates and geometric misalignments. To address this, we introduce SHARE, a pose-free, feed-forward Gaussian splatting framework that overcomes these ambiguities by joint shape and camera rays estimation. Instead of relying on explicit 3D transformations, SHARE builds a pose-aware canonical volume representation that seamlessly integrates multi-view information, reducing misalignment caused by inaccurate pose estimates. Additionally, anchor-aligned Gaussian prediction enhances scene reconstruction by refining local geometry around coarse anchors, allowing for more precise Gaussian placement. Extensive experiments on diverse real-world datasets show that our method achieves robust performance in pose-free generalizable Gaussian splatting.

Surf2CT: Cascaded 3D Flow Matching Models for Torso 3D CT Synthesis from Skin Surface

We present Surf2CT, a novel cascaded flow matching framework that synthesizes full 3D computed tomography (CT) volumes of the human torso from external surface scans and simple demographic data (age, sex, height, weight). This is the first approach capable of generating realistic volumetric internal anatomy images solely based on external body shape and demographics, without any internal imaging. Surf2CT proceeds through three sequential stages: (1) Surface Completion, reconstructing a complete signed distance function (SDF) from partial torso scans using conditional 3D flow matching; (2) Coarse CT Synthesis, generating a low-resolution CT volume from the completed SDF and demographic information; and (3) CT Super-Resolution, refining the coarse volume into a high-resolution CT via a patch-wise conditional flow model. Each stage utilizes a 3D-adapted EDM2 backbone trained via flow matching. We trained our model on a combined dataset of 3,198 torso CT scans (approximately 1.13 million axial slices) sourced from Massachusetts General Hospital (MGH) and the AutoPET challenge. Evaluation on 700 paired torso surface-CT cases demonstrated strong anatomical fidelity: organ volumes exhibited small mean percentage differences (range from -11.1% to 4.4%), and muscle/fat body composition metrics matched ground truth with strong correlation (range from 0.67 to 0.96). Lung localization had minimal bias (mean difference -2.5 mm), and surface completion significantly improved metrics (Chamfer distance: from 521.8 mm to 2.7 mm; Intersection-over-Union: from 0.87 to 0.98). Surf2CT establishes a new paradigm for non-invasive internal anatomical imaging using only external data, opening opportunities for home-based healthcare, preventive medicine, and personalized clinical assessments without the risks associated with conventional imaging techniques.

Single Domain Generalization for Alzheimer's Detection from 3D MRIs with Pseudo-Morphological Augmentations and Contrastive Learning

Although Alzheimer's disease detection via MRIs has advanced significantly thanks to contemporary deep learning models, challenges such as class imbalance, protocol variations, and limited dataset diversity often hinder their generalization capacity. To address this issue, this article focuses on the single domain generalization setting, where given the data of one domain, a model is designed and developed with maximal performance w.r.t. an unseen domain of distinct distribution. Since brain morphology is known to play a crucial role in Alzheimer's diagnosis, we propose the use of learnable pseudo-morphological modules aimed at producing shape-aware, anatomically meaningful class-specific augmentations in combination with a supervised contrastive learning module to extract robust class-specific representations. Experiments conducted across three datasets show improved performance and generalization capacity, especially under class imbalance and imaging protocol variations. The source code will be made available upon acceptance at https://github.com/zobia111/SDG-Alzheimer.

Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud

Gaussian Splatting (GS) has gained attention as a fast and effective method for novel view synthesis. It has also been applied to 3D reconstruction using multi-view images and can achieve fast and accurate 3D reconstruction. However, GS assumes that the input contains a large number of multi-view images, and therefore, the reconstruction accuracy significantly decreases when only a limited number of input images are available. One of the main reasons is the insufficient number of 3D points in the sparse point cloud obtained through Structure from Motion (SfM), which results in a poor initialization for optimizing the Gaussian primitives. We propose a new 3D reconstruction method, called Sparse2DGS, to enhance 2DGS in reconstructing objects using only three images. Sparse2DGS employs DUSt3R, a fundamental model for stereo images, along with COLMAP MVS to generate highly accurate and dense 3D point clouds, which are then used to initialize 2D Gaussians. Through experiments on the DTU dataset, we show that Sparse2DGS can accurately reconstruct the 3D shapes of objects using just three images.

From Single Images to Motion Policies via Video-Generation Environment Representations

Autonomous robots typically need to construct representations of their surroundings and adapt their motions to the geometry of their environment. Here, we tackle the problem of constructing a policy model for collision-free motion generation, consistent with the environment, from a single input RGB image. Extracting 3D structures from a single image often involves monocular depth estimation. Developments in depth estimation have given rise to large pre-trained models such as DepthAnything. However, using outputs of these models for downstream motion generation is challenging due to frustum-shaped errors that arise. Instead, we propose a framework known as Video-Generation Environment Representation (VGER), which leverages the advances of large-scale video generation models to generate a moving camera video conditioned on the input image. Frames of this video, which form a multiview dataset, are then input into a pre-trained 3D foundation model to produce a dense point cloud. We then introduce a multi-scale noise approach to train an implicit representation of the environment structure and build a motion generation model that complies with the geometry of the representation. We extensively evaluate VGER over a diverse set of indoor and outdoor environments. We demonstrate its ability to produce smooth motions that account for the captured geometry of a scene, all from a single RGB input image.

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduce Direct3D-S2, a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs. Our key innovation is the Spatial Sparse Attention (SSA) mechanism, which greatly enhances the efficiency of Diffusion Transformer (DiT) computations on sparse volumetric data. SSA allows the model to effectively process large token sets within sparse volumes, substantially reducing computational overhead and achieving a 3.9x speedup in the forward pass and a 9.6x speedup in the backward pass. Our framework also includes a variational autoencoder (VAE) that maintains a consistent sparse volumetric format across input, latent, and output stages. Compared to previous methods with heterogeneous representations in 3D VAE, this unified design significantly improves training efficiency and stability. Our model is trained on public available datasets, and experiments demonstrate that Direct3D-S2 not only surpasses state-of-the-art methods in generation quality and efficiency, but also enables training at 1024 resolution using only 8 GPUs, a task typically requiring at least 32 GPUs for volumetric representations at 256 resolution, thus making gigascale 3D generation both practical and accessible. Project page: https://www.neural4d.com/research/direct3d-s2.

Disentangled Human Body Representation Based on Unsupervised Semantic-Aware Learning

In recent years, more and more attention has been paid to the learning of 3D human representation. However, the complexity of lots of hand-defined human body constraints and the absence of supervision data limit that the existing works controllably and accurately represent the human body in views of semantics and representation ability. In this paper, we propose a human body representation with controllable fine-grained semantics and high precison of reconstruction in an unsupervised learning framework. In particularly, we design a whole-aware skeleton-grouped disentangle strategy to learn a correspondence between geometric semantical measurement of body and latent codes, which facilitates the control of shape and posture of human body by modifying latent coding paramerers. With the help of skeleton-grouped whole-aware encoder and unsupervised disentanglement losses, our representation model is learned by an unsupervised manner. Besides, a based-template residual learning scheme is injected into the encoder to ease of learning human body latent parameter in complicated body shape and pose spaces. Because of the geometrically meaningful latent codes, it can be used in a wide range of applications, from human body pose transfer to bilinear latent code interpolation. Further more, a part-aware decoder is utlized to promote the learning of controllable fine-grained semantics. The experimental results on public 3D human datasets show that the method has the ability of precise reconstruction.

Canonical Pose Reconstruction from Single Depth Image for 3D Non-rigid Pose Recovery on Limited Datasets

3D reconstruction from 2D inputs, especially for non-rigid objects like humans, presents unique challenges due to the significant range of possible deformations. Traditional methods often struggle with non-rigid shapes, which require extensive training data to cover the entire deformation space. This study addresses these limitations by proposing a canonical pose reconstruction model that transforms single-view depth images of deformable shapes into a canonical form. This alignment facilitates shape reconstruction by enabling the application of rigid object reconstruction techniques, and supports recovering the input pose in voxel representation as part of the reconstruction task, utilizing both the original and deformed depth images. Notably, our model achieves effective results with only a small dataset of approximately 300 samples. Experimental results on animal and human datasets demonstrate that our model outperforms other state-of-the-art methods.

Equivariant Flow Matching for Point Cloud Assembly

The goal of point cloud assembly is to reconstruct a complete 3D shape by aligning multiple point cloud pieces. This work presents a novel equivariant solver for assembly tasks based on flow matching models. We first theoretically show that the key to learning equivariant distributions via flow matching is to learn related vector fields. Based on this result, we propose an assembly model, called equivariant diffusion assembly (Eda), which learns related vector fields conditioned on the input pieces. We further construct an equivariant path for Eda, which guarantees high data efficiency of the training process. Our numerical results show that Eda is highly competitive on practical datasets, and it can even handle the challenging situation where the input pieces are non-overlapped.