naveen manwani (@NaveenManwani17)
2025-05-11 | ❤️ 44 | 🔁 7
🚨CVPR 2025 Paper Alert 🚨
➡️Paper Title: EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis
🌟Few pointers from the paper
🎯Novel view synthesis of urban scenes is essential for autonomous driving-related this NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.
🎯Authors of this paper introduced “EVolSplat”, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
🎯Unlike existing feed-forward, pixel-aligned 3DGS methods, which often suffer from issues like multi-view inconsistencies and duplicated content, their approach predicts 3D Gaussians across multiple frames within a unified volume using a 3D convolutional network.
🎯This is achieved by initializing 3D Gaussians with noisy depth predictions, and then refining their geometric properties in 3D space and predicting color based on 2D textures.
🎯Their model also handles distant views and the sky with a flexible hemisphere background model.
🎯This enabled them to perform fast, feed-forward reconstruction while achieving real-time rendering.
🎯Experimental evaluations on the KITTI-360 and Waymo datasets showed that their method achieves state-of-the-art quality compared to existing feed-forward 3DGS- and NeRF-based methods.
🏢Organization: @ZJU_China , @Huawei Noah’s Ark Lab, @uni_tue , Tübingen AI Center
🧙Paper Authors: Sheng Miao, @JiaxinHuang2001 , Dongfeng Bai, Xu Yan, Hongyu Zhou, Yue Wang, Bingbing Liu, Andreas Geiger, Yiyi Liao
📝 Read the Full Paper here: https://arxiv.org/abs/2503.20168
🗂️ Project Page: https://xdimlab.github.io/EVolSplat/
🧑💻 Code: https://github.com/Miaosheng1/EVolSplat
🎥 Be sure to watch the attached Demo Video - Sound on 🔊🔊
Find this Valuable 💎 ?
♻️QT and teach your network something new
Follow me 👣, @NaveenManwani17 , for the latest updates on Tech and AI-related news, insightful research papers, and exciting announcements.
🔗 원본 링크
- https://arxiv.org/abs/2503.20168
- https://xdimlab.github.io/EVolSplat/
- https://github.com/Miaosheng1/EVolSplat
미디어
🔗 Related
Auto-generated - needs manual review
Tags
domain-vision-3d domain-rendering domain-ai-ml domain-dev-tools domain-visionos