CyberSec Research

Randomly sampling points on surfaces is an essential operation in geometry processing. This sampling is computationally straightforward on explicit meshes, but it is much more difficult on other shape representations, such as widely-used implicit surfaces. This work studies a simple and general scheme for sampling points on a surface, which is derived from a connection to the intersections of random rays with the surface. Concretely, given a subroutine to cast a ray against a surface and find all intersections, we can use that subroutine to uniformly sample white noise points on the surface. This approach is particularly effective in the context of implicit signed distance functions, where sphere marching allows us to efficiently cast rays and sample points, without needing to extract an intermediate mesh. We analyze the basic method to show that it guarantees uniformity, and find experimentally that it is significantly more efficient than alternative strategies on a variety of representations. Furthermore, we show extensions to blue noise sampling and stratified sampling, and applications to deform neural implicit surfaces as well as moment estimation.

Neurosurgery increasingly uses Mixed Reality (MR) technologies for intraoperative assistance. The greatest challenge in this area is mentally reconstructing complex 3D anatomical structures from 2D slices with millimetric precision, which is required in procedures like External Ventricular Drain (EVD) placement. MR technologies have shown great potential in improving surgical performance, however, their limited availability in clinical settings underscores the need for training systems that foster skill retention in unaided conditions. In this paper, we introduce NeuroMix, an MR-based simulator for EVD placement. We conduct a study with 48 participants to assess the impact of 2D and 3D visual aids on usability, cognitive load, technology acceptance, and procedure precision and execution time. Three training modalities are compared: one without visual aids, one with 2D aids only, and one combining both 2D and 3D aids. The training phase takes place entirely on digital objects, followed by a freehand EVD placement testing phase performed with a physical catherer and a physical phantom without MR aids. We then compare the participants performance with that of a control group that does not undergo training. Our findings show that participants trained with both 2D and 3D aids achieve a 44\% improvement in precision during unaided testing compared to the control group, substantially higher than the improvement observed in the other groups. All three training modalities receive high usability and technology acceptance ratings, with significant equivalence across groups. The combination of 2D and 3D visual aids does not significantly increase cognitive workload, though it leads to longer operation times during freehand testing compared to the control group.

As one of the first research teams with full access to Siemens' Cinematic Reality, we evaluate its usability and clinical potential for cinematic volume rendering on the Apple Vision Pro. We visualized venous-phase liver computed tomography and magnetic resonance cholangiopancreatography scans from the CHAOS and MRCP\_DLRecon datasets. Fourteen medical experts assessed usability and anticipated clinical integration potential using the System Usability Scale, ISONORM 9242-110-S questionnaire, and an open-ended survey. Their feedback identified feasibility, key usability strengths, and required features to catalyze the adaptation in real-world clinical workflows. The findings provide insights into the potential of immersive cinematic rendering in medical imaging.

Medical imaging segmentation is essential in clinical settings for diagnosing diseases, planning surgeries, and other procedures. However, manual annotation is a cumbersome and effortful task. To mitigate these aspects, this study implements and evaluates the usability and clinical applicability of an extended reality (XR)-based segmentation tool for anatomical CT scans, using the Meta Quest 3 headset and Logitech MX Ink stylus. We develop an immersive interface enabling real-time interaction with 2D and 3D medical imaging data in a customizable workspace designed to mitigate workflow fragmentation and cognitive demands inherent to conventional manual segmentation tools. The platform combines stylus-driven annotation, mirroring traditional pen-on-paper workflows, with instant 3D volumetric rendering. A user study with a public craniofacial CT dataset demonstrated the tool's foundational viability, achieving a System Usability Scale (SUS) score of 66, within the expected range for medical applications. Participants highlighted the system's intuitive controls (scoring 4.1/5 for self-descriptiveness on ISONORM metrics) and spatial interaction design, with qualitative feedback highlighting strengths in hybrid 2D/3D navigation and realistic stylus ergonomics. While users identified opportunities to enhance task-specific precision and error management, the platform's core workflow enabled dynamic slice adjustment, reducing cognitive load compared to desktop tools. Results position the XR-stylus paradigm as a promising foundation for immersive segmentation tools, with iterative refinements targeting haptic feedback calibration and workflow personalization to advance adoption in preoperative planning.

This work introduces a contact interaction methodology for an unbiased treatment of contacting surfaces without assigning surfaces as master and slave. The contact tractions between interacting discrete segments are evaluated with respect to a midplane in a single pass, inherently maintaining the equilibrium of tractions. These tractions are based on the penalisation of true interpenetration between opposite surfaces, and the procedure of their integral for discrete contacting segments is described in this paper. A meticulous examination of the different possible geometric configurations of interacting 3D segments is presented to develop visual understanding and better traction evaluation accuracy. The accuracy and robustness of the proposed method are validated against the analytical solutions of the contact patch test, two-beam bending, Hertzian contact, and flat punch test, thus proving the capability to reproduce contact between flat surfaces, curved surfaces, and sharp corners in contact, respectively. The method passes the contact patch test with the uniform transmission of contact pressure matching the accuracy levels of finite elements. It converges towards the analytical solution with mesh refinement and a suitably high penalty factor. The effectiveness of the proposed algorithm also extends to self-contact problems and has been tested for self-contact between flat and curved surfaces with inelastic material. Dynamic problems of elastic and inelastic collisions between bars, as well as oblique collisions of cylinders, are also presented. The ability of the algorithm to resolve contacts between flat and curved surfaces for nonconformal meshes with high accuracy demonstrates its versatility in general contact problems.

This paper proposes a fast and unsupervised scheme for a polygonal approximation of a closed digital curve. It is demonstrated that the approximation scheme is faster than state-of-the-art approximation and is competitive with the same in Rosin's measure and in its aesthetic aspect. The scheme comprises of three phases: initial segmentation, iterative vertex insertion, and iterative merging, followed by vertex adjustment. The initial segmentation is used to detect sharp turnings - the vertices that seemingly have high curvature. It is likely that some of important vertices with low curvature might have been missed out at the first phase and so iterative vertex insertion is used to add vertices in a region where the curvature changes slowly but steadily. The initial phase may pick up some undesirable vertices and so merging is used to eliminate the redundant vertices. Finally, vertex adjustment is used to facilitate enhancement in the aesthetic look of the approximation. The quality of the approximations is measured using Rosin's measure. The robustness of the proposed scheme with respect to geometric transformation is observed.

3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate it as a dense segmentation task, independently classifying each voxel. However, this paradigm neglects critical instance-centric discriminability, leading to instance-level incompleteness and adjacent ambiguities. To address this, we highlight a free lunch of occupancy labels: the voxel-level class label implicitly provides insight at the instance level, which is overlooked by the community. Motivated by this observation, we first introduce a training-free Voxel-to-Instance (VoxNT) trick: a simple yet effective method that freely converts voxel-level class labels into instance-level offset labels. Building on this, we further propose VoxDet, an instance-centric framework that reformulates the voxel-level occupancy prediction as dense object detection by decoupling it into two sub-tasks: offset regression and semantic prediction. Specifically, based on the lifted 3D volume, VoxDet first uses (a) Spatially-decoupled Voxel Encoder to generate disentangled feature volumes for the two sub-tasks, which learn task-specific spatial deformation in the densely projected tri-perceptive space. Then, we deploy (b) Task-decoupled Dense Predictor to address this task via dense detection. Here, we first regress a 4D offset field to estimate distances (6 directions) between voxels and object borders in the voxel space. The regressed offsets are then used to guide the instance-level aggregation in the classification branch, achieving instance-aware prediction. Experiments show that VoxDet can be deployed on both camera and LiDAR input, jointly achieving state-of-the-art results on both benchmarks. VoxDet is not only highly efficient, but also achieves 63.0 IoU on the SemanticKITTI test set, ranking 1st on the online leaderboard.

Mesh deformation is a fundamental tool in 3D content manipulation. Despite extensive prior research, existing approaches often suffer from low output quality, require significant manual tuning, or depend on data-intensive training. To address these limitations, we introduce a training-free, handle-based mesh deformation method. % Our core idea is to leverage a Vision-Language Model (VLM) to interpret and manipulate a handle-based interface through prompt engineering. We begin by applying cone singularity detection to identify a sparse set of potential handles. The VLM is then prompted to select both the deformable sub-parts of the mesh and the handles that best align with user instructions. Subsequently, we query the desired deformed positions of the selected handles in screen space. To reduce uncertainty inherent in VLM predictions, we aggregate the results from multiple camera views using a novel multi-view voting scheme. % Across a suite of benchmarks, our method produces deformations that align more closely with user intent, as measured by CLIP and GPTEval3D scores, while introducing low distortion -- quantified via membrane energy. In summary, our approach is training-free, highly automated, and consistently delivers high-quality mesh deformations.

In this paper, we investigate the challenges associated with using egocentric devices to photorealistic reconstruct the scene in high dynamic range. Existing methodologies typically assume using frame-rate 6DoF pose estimated from the device's visual-inertial odometry system, which may neglect crucial details necessary for pixel-accurate reconstruction. This study presents two significant findings. Firstly, in contrast to mainstream work treating RGB camera as global shutter frame-rate camera, we emphasize the importance of employing visual-inertial bundle adjustment (VIBA) to calibrate the precise timestamps and movement of the rolling shutter RGB sensing camera in a high frequency trajectory format, which ensures an accurate calibration of the physical properties of the rolling-shutter camera. Secondly, we incorporate a physical image formation model based into Gaussian Splatting, which effectively addresses the sensor characteristics, including the rolling-shutter effect of RGB cameras and the dynamic ranges measured by sensors. Our proposed formulation is applicable to the widely-used variants of Gaussian Splats representation. We conduct a comprehensive evaluation of our pipeline using the open-source Project Aria device under diverse indoor and outdoor lighting conditions, and further validate it on a Meta Quest3 device. Across all experiments, we observe a consistent visual enhancement of +1 dB in PSNR by incorporating VIBA, with an additional +1 dB achieved through our proposed image formation model. Our complete implementation, evaluation datasets, and recording profile are available at http://www.projectaria.com/photoreal-reconstruction/

Creating accurate, physical simulations directly from real-world robot motion holds great value for safe, scalable, and affordable robot learning, yet remains exceptionally challenging. Real robot data suffers from occlusions, noisy camera poses, dynamic scene elements, which hinder the creation of geometrically accurate and photorealistic digital twins of unseen objects. We introduce a novel real-to-sim framework tackling all these challenges at once. Our key insight is a hybrid scene representation merging the photorealistic rendering of 3D Gaussian Splatting with explicit object meshes suitable for physics simulation within a single representation. We propose an end-to-end optimization pipeline that leverages differentiable rendering and differentiable physics within MuJoCo to jointly refine all scene components - from object geometry and appearance to robot poses and physical parameters - directly from raw and imprecise robot trajectories. This unified optimization allows us to simultaneously achieve high-fidelity object mesh reconstruction, generate photorealistic novel views, and perform annotation-free robot pose calibration. We demonstrate the effectiveness of our approach both in simulation and on challenging real-world sequences using an ALOHA 2 bi-manual manipulator, enabling more practical and robust real-to-simulation pipelines.

We propose a novel diffusion-based framework for automatic colorization of Anime-style facial sketches. Our method preserves the structural fidelity of the input sketch while effectively transferring stylistic attributes from a reference image. Unlike traditional approaches that rely on predefined noise schedules - which often compromise perceptual consistency -- our framework builds on continuous-time diffusion models and introduces SSIMBaD (Sigma Scaling with SSIM-Guided Balanced Diffusion). SSIMBaD applies a sigma-space transformation that aligns perceptual degradation, as measured by structural similarity (SSIM), in a linear manner. This scaling ensures uniform visual difficulty across timesteps, enabling more balanced and faithful reconstructions. Experiments on a large-scale Anime face dataset demonstrate that our method outperforms state-of-the-art models in both pixel accuracy and perceptual quality, while generalizing to diverse styles. Code is available at github.com/Giventicket/SSIMBaD-Sigma-Scaling-with-SSIM-Guided-Balanced-Diffusion-for-AnimeFace-Colorization

Reconstructing articulated objects prevalent in daily environments is crucial for applications in augmented/virtual reality and robotics. However, existing methods face scalability limitations (requiring 3D supervision or costly annotations), robustness issues (being susceptible to local optima), and rendering shortcomings (lacking speed or photorealism). We introduce SplArt, a self-supervised, category-agnostic framework that leverages 3D Gaussian Splatting (3DGS) to reconstruct articulated objects and infer kinematics from two sets of posed RGB images captured at different articulation states, enabling real-time photorealistic rendering for novel viewpoints and articulations. SplArt augments 3DGS with a differentiable mobility parameter per Gaussian, achieving refined part segmentation. A multi-stage optimization strategy is employed to progressively handle reconstruction, part segmentation, and articulation estimation, significantly enhancing robustness and accuracy. SplArt exploits geometric self-supervision, effectively addressing challenging scenarios without requiring 3D annotations or category-specific priors. Evaluations on established and newly proposed benchmarks, along with applications to real-world scenarios using a handheld RGB camera, demonstrate SplArt's state-of-the-art performance and real-world practicality. Code is publicly available at https://github.com/ripl/splart.

Existing facial appearance capture methods can reconstruct plausible facial reflectance from smartphone-recorded videos. However, the reconstruction quality is still far behind the ones based on studio recordings. This paper fills the gap by developing a novel daily-used solution with a co-located smartphone and flashlight video capture setting in a dim room. To enhance the quality, our key observation is to solve facial reflectance maps within the data distribution of studio-scanned ones. Specifically, we first learn a diffusion prior over the Light Stage scans and then steer it to produce the reflectance map that best matches the captured images. We propose to train the diffusion prior at the patch level to improve generalization ability and training stability, as current Light Stage datasets are in ultra-high resolution but limited in data size. Tailored to this prior, we propose a patch-level posterior sampling technique to sample seamless full-resolution reflectance maps from this patch-level diffusion model. Experiments demonstrate our method closes the quality gap between low-cost and studio recordings by a large margin, opening the door for everyday users to clone themselves to the digital world. Our code will be released at https://github.com/yxuhan/DoRA.

We present MS-Splatting -- a multi-spectral 3D Gaussian Splatting (3DGS) framework that is able to generate multi-view consistent novel views from images of multiple, independent cameras with different spectral domains. In contrast to previous approaches, our method does not require cross-modal camera calibration and is versatile enough to model a variety of different spectra, including thermal and near-infra red, without any algorithmic changes. Unlike existing 3DGS-based frameworks that treat each modality separately (by optimizing per-channel spherical harmonics) and therefore fail to exploit the underlying spectral and spatial correlations, our method leverages a novel neural color representation that encodes multi-spectral information into a learned, compact, per-splat feature embedding. A shallow multi-layer perceptron (MLP) then decodes this embedding to obtain spectral color values, enabling joint learning of all bands within a unified representation. Our experiments show that this simple yet effective strategy is able to improve multi-spectral rendering quality, while also leading to improved per-spectra rendering quality over state-of-the-art methods. We demonstrate the effectiveness of this new technique in agricultural applications to render vegetation indices, such as normalized difference vegetation index (NDVI).

3D human reconstruction and animation are long-standing topics in computer graphics and vision. However, existing methods typically rely on sophisticated dense-view capture and/or time-consuming per-subject optimization procedures. To address these limitations, we propose HumanRAM, a novel feed-forward approach for generalizable human reconstruction and animation from monocular or sparse human images. Our approach integrates human reconstruction and animation into a unified framework by introducing explicit pose conditions, parameterized by a shared SMPL-X neural texture, into transformer-based large reconstruction models (LRM). Given monocular or sparse input images with associated camera parameters and SMPL-X poses, our model employs scalable transformers and a DPT-based decoder to synthesize realistic human renderings under novel viewpoints and novel poses. By leveraging the explicit pose conditions, our model simultaneously enables high-quality human reconstruction and high-fidelity pose-controlled animation. Experiments show that HumanRAM significantly surpasses previous methods in terms of reconstruction accuracy, animation fidelity, and generalization performance on real-world datasets. Video results are available at https://zju3dv.github.io/humanram/.

In this paper, we present TalkingMachines -- an efficient framework that transforms pretrained video generation models into real-time, audio-driven character animators. TalkingMachines enables natural conversational experiences by integrating an audio large language model (LLM) with our video generation foundation model. Our primary contributions include: (1) We adapt a pretrained SOTA image-to-video DiT into an audio-driven avatar generation model of 18 billion parameters; (2) We enable infinite video streaming without error accumulation through asymmetric knowledge distillation from a bidirectional teacher model into a sparse causal, autoregressive student model; (3) We design a high-throughput, low-latency inference pipeline incorporating several key engineering optimizations such as: (a) disaggregation of the DiT and VAE decoder across separate devices, (b) efficient overlap of inter-device communication and computation using CUDA streams, (c) elimination of redundant recomputations to maximize frame-generation throughput. Please see demo videos here - https://aaxwaz.github.io/TalkingMachines/

We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with effectively learning fine-grained concepts or require a large dataset as input. We propose a dynamic data synthesis pipeline generating diverse part compositions to address one-shot data scarcity. Most importantly, we propose to maximize the mutual information between denoised latents and structured concept codes via a concept predictor, enabling direct regulation on concept disentanglement and re-composition supervision. Our method achieves strong disentanglement and controllable composition, outperforming subject and part-level baselines when mixing concepts from the same, or different, object categories.

Accurate food volume estimation is crucial for dietary monitoring, medical nutrition management, and food intake analysis. Existing 3D Food Volume estimation methods accurately compute the food volume but lack for food portions selection. We present VolTex, a framework that improves \change{the food object selection} in food volume estimation. Allowing users to specify a target food item via text input to be segmented, our method enables the precise selection of specific food objects in real-world scenes. The segmented object is then reconstructed using the Neural Surface Reconstruction method to generate high-fidelity 3D meshes for volume computation. Extensive evaluations on the MetaFood3D dataset demonstrate the effectiveness of our approach in isolating and reconstructing food items for accurate volume estimation. The source code is accessible at https://github.com/GCVCG/VolTex.