Results 231 to 240 of about 2,709,443 (248)

TECA: Text-Guided Generation and Editing of Compositional 3D Avatars

International Conference on 3D Vision, 2023
Our goal is to create a realistic 3D facial avatar with hair and accessories using only a text description. While this challenge has attracted significant recent interest, existing methods either lack realism, produce unrealistic shapes, or do not ...
Hao Zhang, Yao Feng, Peter Kulits, Yandong Wen, Justus Thies, Michael J. Black   +5 more
semanticscholar   +1 more source

Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture

International Conference on 3D Vision, 2023
Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details.
Yixin Chen, Junfeng Ni, Nan Jiang, Yaowei Zhang, Yixin Zhu, Siyuan Huang   +5 more
semanticscholar   +1 more source

3D Reconstruction with Spatial Memory

International Conference on 3D Vision
We present Spann3R, a novel approach for dense 3D reconstruction from ordered or unordered image collections. Built on the DUSt3R paradigm, Spann3R uses a transformer-based architecture to directly regress pointmaps from images without any prior ...
Hengyi Wang, Lourdes Agapito
semanticscholar   +1 more source

Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

International Conference on 3D Vision
We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a 'foundation' model for monocular depth estimation and extend it to a ...
Stanislaw Szymanowicz, Eldar Insafutdinov, Chuanxia Zheng, Dylan Campbell, João F. Henriques, Christian Rupprecht, Andrea Vedaldi   +6 more
semanticscholar   +1 more source

RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion

International Conference on 3D Vision
We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models.
Jaidev Shriram, Alex Trevithick, Lingjie Liu, Ravi Ramamoorthi   +3 more
semanticscholar   +1 more source

LoopSplat: Loop Closure by Registering 3D Gaussian Splats

International Conference on 3D Vision
Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian Splats (3DGS) has recently shown promise towards more accurate, dense 3D scene maps.
Liyuan Zhu, Yue Li, Erik Sandström, Shengyu Huang, Konrad Schindler, Iro Armeni   +5 more
semanticscholar   +1 more source

Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering

International Conference on 3D Vision
We introduce a highly efficient method for panoptic segmentation of large 3D point clouds by redefining this task as a scalable graph clustering problem.
Damien Robert, Hugo Raguet, Loic Landrieu   +2 more
semanticscholar   +1 more source

HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors

International Conference on 3D Vision
In this paper, we present a novel 3D head avatar creation approach capable of generalizing from few-shot in-the-wild data with high-fidelity and animatable robustness.
Xiaozheng Zheng, Chao Wen, Zhaohu Li, Weiyi Zhang, Zhuo Su, Xu Chang, Yang Zhao, Zheng Lv, Xiaoyuan Zhang, Yongjie Zhang, Guidong Wang, Lan Xu   +11 more
semanticscholar   +1 more source

Garment3DGen: 3D Garment Stylization and Texture Generation

International Conference on 3D Vision
We introduce Garment3DGen a new method to synthesize 3D garment assets from a base mesh given a single input image as guidance. Our proposed approach allows users to generate 3D textured clothes based on both real and synthetic images, such as those ...
N. Sarafianos, Tuur Stuyck, Xiaoyu Xiang, Yilei Li, Jovan Popovic, Rakesh Ranjan   +5 more
semanticscholar   +1 more source

WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting

International Conference on 3D Vision
The underwater 3D scene reconstruction is a challenging, yet interesting problem with applications ranging from naval robots to VR experiences. The problem was successfully tackled by fully volumetric NeRF-based methods which can model both the geometry ...
Huapeng Li, Wenxuan Song, Tianao Xu, Alexandre Elsig, Jonáš Kulhánek   +4 more
semanticscholar   +1 more source