Google 학술 검색

SLGaussian: Fast Language Gaussian Splatting in Sparse Views

K Chen, BQ Dai, M Qin, D Zhang, P Li, Y Zou… - arxiv preprint arxiv …, 2024 - arxiv.org

3D semantic field learning is crucial for applications like autonomous navigation, AR/VR,
and robotics, where accurate comprehension of 3D scenes from limited viewpoints is …

저장 인용 2회 인용 관련 학술자료 전체 2개의 버전 HTML 버전

Integrating Meshes and 3D Gaussians for Indoor Scene Reconstruction with SAM Mask Guidance

J Kim, J Lim - arxiv preprint arxiv:2407.16173, 2024 - arxiv.org

We present a novel approach for 3D indoor scene reconstruction that combines 3D
Gaussian Splatting (3DGS) with mesh representations. We use meshes for the room layout …

Generalizable 3D Gaussian Splatting for novel view synthesis

C Zhao, X Huang, K Yang, X Wang, Q Wang - Pattern Recognition, 2025 - Elsevier

We present a generalizable 3D Gaussian Splatting (3DGS) method that can synthesize
novel views of unseen scenes. Existing methods directly input image features into the …

저장 인용 관련 학술자료 전체 2개의 버전

GSemSplat: Generalizable Semantic 3D Gaussian Splatting from Uncalibrated Image Pairs

X Wang, C Lan, H Zhu, Z Chen, Y Lu - arxiv preprint arxiv:2412.16932, 2024 - arxiv.org

Modeling and understanding the 3D world is crucial for various applications, from
augmented reality to robotic navigation. Recent advancements based on 3D Gaussian …

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

C Zhao, X Wang, T Zhang, S Javed… - arxiv preprint arxiv …, 2024 - arxiv.org

3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness for novel view
synthesis (NVS). However, the 3DGS model tends to overfit when trained with sparse posed …

HuGDiffusion: Generalizable Single-Image Human Rendering via 3D Gaussian Diffusion

Y Tang, Q Zhang, J Hou - arxiv preprint arxiv:2501.15008, 2025 - arxiv.org

We present HuGDiffusion, a generalizable 3D Gaussian splatting (3DGS) learning pipeline
to achieve novel view synthesis (NVS) of human characters from single-view input images …

StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation

S Zhai, Z Ye, J Liu, W **e, J Hu, Z Peng, H Xue… - arxiv preprint arxiv …, 2025 - arxiv.org

Recent advances in large reconstruction and generative models have significantly improved
scene reconstruction and novel view generation. However, due to compute limitations, each …

Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting

H Liu, M Chen, Y Ma, H **ao, Y He - arxiv preprint arxiv:2411.18667, 2024 - arxiv.org

Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful
performance on 3D vision tasks, especially when annotations are limited. However, existing …