Searcharxiv⌕ Search

arXiv subjects

Vibekananda Dutta

Publications and source records attributed to Vibekananda Dutta.

3 recordsLinked to original sources

DPGS-SLAM: Diffusion-Prior and Provenance-Aware Monocular Gaussian Splatting SLAM for Dynamic Visual Sensing

This paper presents DPGS-SLAM (Diffusion-Prior and Provenance-Aware Monocular Gaussian Splatting SLAM) for dense mapping in environments containing dynamic objects. Objects in dynamic motion remain a significant challenge for dense visual SLAM since dynamic observations can contaminate camera tracking and scene reconstruction. Although 3DGS (3D Gaussian splatting) enables efficient dense mapping, existing 3DGS-SLAM systems may exhibit instability when dynamic objects violate their underlying static-scene assumption. Excluding dynamic observations can reduce their influence on tracking and mapping, but may leave occluded static backgrounds missing or weakly constrained. Our proposed DPGS-SLAM is a monocular RGB SLAM framework that supports provisional representations of insufficiently observed static backgrounds through asynchronous diffusion-based background completion and provenance-aware Gaussian mapping. Dynamic regions are identified through optical-flow-based motion discovery and temporally consistent mask propagation by SAM2. For selected keyframes, a fine-tuned diffusion inpainting model generates plausible background appearance in occluded regions, while metric depth predicted from completed images initializes provisional Gaussian primitives. Provenance labels distinguish generated primitives from observation-supported primitives, excluding generated content from camera-pose estimation and observed-map optimization. When previously occluded backgrounds become visible, eligible generated primitives are removed, and observation-supported primitives are independently initialized from real RGB observations and predicted depth. Experimental results demonstrated competitive camera tracking, with average ATE RMSE values of 1.2 cm on TUM RGB-D and 2.7 cm on BONN RGB-D datasets. On StaDy4D, DPGS-SLAM improved average PSNR by 4.60 dB over WildGS-SLAM using only monocular RGB input.

cs.RO↗

Networking technologies for robotic applications

The ongoing progress in networking security, together with the growing range of robot applications in many fields of everyday life, makes robotics tangible reality in our near future. Accordingly, new advanced services, depends on the interplay between the robotics and cyber security, are being an important role in robotics world. This paper addresses technological implications of security enhancement to the Internet of Thing (IoT)-aided robotics domain, where networked robots are expected to work in complex environments. The security enhancement suggested by the NIST (National Institute of Standards and Technology) creates a security template for secure communications over the network are also discussed.

cs.CY↗

Novel Architecture for 3D model in virtual communities from detected face

In this research paper we suggest how to extract a face from an image, modify it, characterize it in terms of high-level properties, and apply it to the creation of a personalized avatar. In this research work we tested, we implemented the algorithm on several hundred facial images, including many taken under uncontrolled acquisition conditions, and found to exhibit satisfactory performance for immediate practical use.

cs.CV↗