Related papers: Transparent Checkpoint-Restart for Hardware-Accele…
Reconstructing semantic-aware 3D scenes from sparse views is a challenging yet essential research direction, driven by the demands of emerging applications such as virtual reality and embodied AI. Existing per-scene optimization methods…
The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks. However, we notice one main flaw of re-ranking, i.e., high…
Research into methods for improving the performance of large language models (LLMs) through fine-tuning, retrieval-augmented generation (RAG) and soft-prompting has tended to focus on the use of highly technical or high-cost techniques,…
Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation. Although recent methods achieve high-fidelity reconstructions, they either rely on costly human annotations for object…
FROG is a generic framework dedicated to visualisation of events in high energy experiment. It is suitable to any particular physics experiment or detector design. The code is light (<3 MB) and fast (browsing time ~20 events per second for…
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows,…
While neural 3D reconstruction has advanced substantially, its performance significantly degrades with sparse-view data, which limits its broader applicability, since SfM is often unreliable in sparse-view scenarios where feature matches…
As high-performance computing and AI workloads become increasingly dependent on GPUs, maintaining high performance across rapidly evolving hardware generations has become a major challenge. Developers often spend months tuning scientific…
3D intelligence leverages rich 3D features and stands as a promising frontier in AI, with 3D rendering fundamental to many downstream applications. 3D Gaussian Splatting (3DGS), an emerging high-quality 3D rendering method, requires…
Graph coloring has been broadly used to discover concurrency in parallel computing. To speedup graph coloring for large-scale datasets, parallel algorithms have been proposed to leverage modern GPUs. Existing GPU implementations either have…
Reconstructing transparent objects using affordable RGB-D cameras is a persistent challenge in robotic perception due to inconsistent appearances across views in the RGB domain and inaccurate depth readings in each single-view. We introduce…
3D image registration is one of the most fundamental and computationally expensive operations in medical image analysis. Here, we present a mixed-precision, Gauss--Newton--Krylov solver for diffeomorphic registration of two images. Our work…
Replay and rollback attacks threaten cloud application integrity by reintroducing authentic yet stale data through an untrusted storage interface to compromise application decision-making. Prior security frameworks mitigate these attacks by…
The world around us is full of soft objects we perceive and deform with dexterous hand movements. For a robotic hand to control soft objects, it has to acquire online state feedback of the deforming object. While RGB-D cameras can collect…
We discuss an implementation of our 3D radiative transfer (3DRT) framework with the OpenCL paradigm for general GPU computing. We implement the kernel for solving the 3DRT problem in Cartesian coordinates with periodic boundary conditions…
Due to the optical properties, transparent objects often lead depth cameras to generate incomplete or invalid depth data, which in turn reduces the accuracy and reliability of robotic grasping. Existing approaches typically input the RGB-D…
The new non-volatile memory technology relies on data recoverability to achieve the promise of byte-addressable persistence in computer applications. The durable transaction (e.g. logging) is one of the major persistency programming models…
3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D…
A key question in the problem of 3D reconstruction is how to train a machine or a robot to model 3D objects. Many tasks like navigation in real-time systems such as autonomous vehicles directly depend on this problem. These systems usually…
This paper presents a tool for repairing errors in GPU kernels written in CUDA or OpenCL due to data races and barrier divergence. Our novel extension to prior work can also remove barriers that are deemed unnecessary for correctness. We…