Zobrazeno 1 - 10
of 420
pro vyhledávání: '"Gevers, Theo"'
We focus on recovering 3D object pose and shape from single images. This is highly challenging due to strong (self-)occlusions, depth ambiguities, the enormous shape variance, and lack of 3D ground truth for natural images. Recent work relies mostly
Externí odkaz:
http://arxiv.org/abs/2409.16178
Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and generalizability to real-world
Externí odkaz:
http://arxiv.org/abs/2409.10180
In addition to color and textural information, geometry provides important cues for 3D scene reconstruction. However, current reconstruction methods only include geometry at the feature level thus not fully exploiting the geometric information. In co
Externí odkaz:
http://arxiv.org/abs/2408.15608
Existing methods in neural scene reconstruction utilize the Signed Distance Function (SDF) to model the density function. However, in indoor scenes, the density computed from the SDF for a sampled point may not consistently reflect its real importanc
Externí odkaz:
http://arxiv.org/abs/2408.15524
Autor:
Ma, Qi, Li, Yue, Ren, Bin, Sebe, Nicu, Konukoglu, Ender, Gevers, Theo, Van Gool, Luc, Paudel, Danda Pani
3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks. This calls for the 3D understanding directly in this representation space. To facilitate the research in this direction, we first build a large-sca
Externí odkaz:
http://arxiv.org/abs/2408.10906
Designing high-quality indoor 3D scenes is important in many practical applications, such as room planning or game development. Conventionally, this has been a time-consuming process which requires both artistic skill and familiarity with professiona
Externí odkaz:
http://arxiv.org/abs/2407.20727
Autor:
Xing, Xiaoyan, Hu, Vincent Tao, Metzen, Jan Hendrik, Groh, Konrad, Karaoglu, Sezer, Gevers, Theo
This paper introduces a novel approach to illumination manipulation in diffusion models, addressing the gap in conditional image generation with a focus on lighting conditions. We conceptualize the diffusion model as a black-box image render and stra
Externí odkaz:
http://arxiv.org/abs/2407.20785
Existing perception methods for autonomous driving fall short of recognizing unknown entities not covered in the training data. Open-vocabulary methods offer promising capabilities in detecting any object but are limited by user-specified queries rep
Externí odkaz:
http://arxiv.org/abs/2406.09126
Images from outdoor scenes may be taken under various weather conditions. It is well studied that weather impacts the performance of computer vision algorithms and needs to be handled properly. However, existing algorithms model weather condition as
Externí odkaz:
http://arxiv.org/abs/2403.20092
The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal informatio
Externí odkaz:
http://arxiv.org/abs/2312.10217