Researchers at the UCLA Samueli School of Engineering have created a technology capable of producing novel images using photonics — employing only a fraction of the energy and computational steps per ...
Abstract: This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, namely NCLR, focuses on 2D-3D neural ...
During recent national traumas we’ve heard the side argument over “thoughts and prayers.” Something terrible happens, someone sends thoughts and prayers, someone else snaps, “We don’t need your ...
TL;DR: Tencent has unveiled a new artificial intelligence model that generates videos simulating movement through a three-dimensional space using just a single input image. Called HunyuanWorld-Voyager ...
On Tuesday, Tencent released HunyuanWorld-Voyager, a new open-weights AI model that generates 3D-consistent video sequences from a single image, allowing users to pilot a camera path to "explore" ...
Early results show that nearly 10% of shoppers customize a configuration, with approximately 8 pieces per session and a 30% add-to-cart rate. The configurator is accessible directly from e-commerce ...
Official implementation of 'GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model'. The paper has been accepted by ICML 2025. Pre-trained 3D vision models have gained significant attention ...
Abstract: Estimating dense point-to-point correspondences between two isometric shapes represented as 3D point clouds is a fundamental problem in geometry processing, with applications in texture and ...
UniPre3D is the first unified pre-training method for 3D point clouds that effectively handles both object- and scene-level data through cross-modal Gaussian splatting. Our proposed pre-training task ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback