arXiv subjects

Gregoire Phillips

Publications and source records attributed to Gregoire Phillips.

5 recordsLinked to original sources

arXiv2026

Studying Mobile Spatial Collaboration across Video Calls and Augmented Reality

Mobile video calls are widely used to share information about real-world objects and environments with remote collaborators. While these calls provide valuable visual context in real time, the experience of interacting with people and moving around a space is significantly reduced when compared to co-located conversations. Recent work has demonstrated the potential of Mobile Augmented Reality applications to enable more spatial forms of collaboration across distance. To better understand the dynamics of mobile AR collaboration and how this medium compares against the status quo, we conducted a comparative structured observation study to analyze people's perception of space and interaction with remote collaborators across mobile video calls and AR-based calls. Fourteen pairs of participants completed a spatial collaboration task using each medium. Through a mixed-methods analysis of session videos, transcripts, motion logs, post-task exercises, and interviews, we highlight how the choice of medium influences the roles and responsibilities that collaborators take on and the construction of a shared language for coordination. We discuss the importance of spatial reasoning with one's body, how video calls help participants "be on the same page" more directly, and how AR calls enable both onsite and remote collaborators to engage with the space and each other in ways that resemble in-person interaction. Our study offers a nuanced view of the benefits and limitations of both mediums, and we conclude with a discussion of design implications for future systems that integrate mobile video and AR to better support spatial collaboration in its many forms.

cs.HC↗

arXiv2025

Hierarchical Neural Surfaces for 3D Mesh Compression

Implicit Neural Representations (INRs) have been demonstrated to achieve state-of-the-art compression of a broad range of modalities such as images, videos, 3D surfaces, and audio. Most studies have focused on building neural counterparts of traditional implicit representations of 3D geometries, such as signed distance functions. However, the triangle mesh-based representation of geometry remains the most widely used representation in the industry, while building INRs capable of generating them has been sparsely studied. In this paper, we present a method for building compact INRs of zero-genus 3D manifolds. Our method relies on creating a spherical parameterization of a given 3D mesh - mapping the surface of a mesh to that of a unit sphere - then constructing an INR that encodes the displacement vector field defined continuously on its surface that regenerates the original shape. The compactness of our representation can be attributed to its hierarchical structure, wherein it first recovers the coarse structure of the encoded surface before adding high-frequency details to it. Once the INR is computed, 3D meshes of arbitrary resolution/connectivity can be decoded from it. The decoding can be performed in real time while achieving a state-of-the-art trade-off between reconstruction quality and the size of the compressed representations.

cs.CG↗

arXiv2025

PIT-QMM: A Large Multimodal Model For No-Reference Point Cloud Quality Assessment

Large Multimodal Models (LMMs) have recently enabled considerable advances in the realm of image and video quality assessment, but this progress has yet to be fully explored in the domain of 3D assets. We are interested in using these models to conduct No-Reference Point Cloud Quality Assessment (NR-PCQA), where the aim is to automatically evaluate the perceptual quality of a point cloud in absence of a reference. We begin with the observation that different modalities of data - text descriptions, 2D projections, and 3D point cloud views - provide complementary information about point cloud quality. We then construct PIT-QMM, a novel LMM for NR-PCQA that is capable of consuming text, images and point clouds end-to-end to predict quality scores. Extensive experimentation shows that our proposed method outperforms the state-of-the-art by significant margins on popular benchmarks with fewer training iterations. We also demonstrate that our framework enables distortion localization and identification, which paves a new way forward for model explainability and interactivity. Code and datasets are available at https://www.github.com/shngt/pit-qmm.

cs.CV↗

arXiv2025

Mesh Compression with Quantized Neural Displacement Fields

Implicit neural representations (INRs) have been successfully used to compress a variety of 3D surface representations such as Signed Distance Functions (SDFs), voxel grids, and also other forms of structured data such as images, videos, and audio. However, these methods have been limited in their application to unstructured data such as 3D meshes and point clouds. This work presents a simple yet effective method that extends the usage of INRs to compress 3D triangle meshes. Our method encodes a displacement field that refines the coarse version of the 3D mesh surface to be compressed using a small neural network. Once trained, the neural network weights occupy much lower memory than the displacement field or the original surface. We show that our method is capable of preserving intricate geometric textures and demonstrates state-of-the-art performance for compression ratios ranging from 4x to 380x.

cs.GR↗

arXiv2024

Snail: Secure Single Iteration Localization

Localization is a computer vision task by which the position and orientation of a camera is determined from an image and environmental map. We propose a method for performing localization in a privacy preserving manner supporting two scenarios: first, when the image and map are held by a client who wishes to offload localization to untrusted third parties, and second, when the image and map are held separately by untrusting parties. Privacy preserving localization is necessary when the image and map are confidential, and offloading conserves on-device power and frees resources for other tasks. To accomplish this we integrate existing localization methods and secure multi-party computation (MPC), specifically garbled circuits, yielding proof-based security guarantees in contrast to existing obfuscation-based approaches which recent related work has shown vulnerable. We present two approaches to localization, a baseline data-oblivious adaptation of localization suitable for garbled circuits and our novel Single Iteration Localization. Our technique improves overall performance while maintaining confidentiality of the input image, map, and output pose at the expense of increased communication rounds but reduced computation and communication required per round. Single Iteration Localization is over two orders of magnitude faster than a straightforward application of garbled circuits to localization enabling real-world usage in the first robot to offload localization without revealing input images, environmental map, position, or orientation to offload servers.

cs.CR↗