[PDF][PDF] Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds

Z Fan, W Cong, K Wen, K Wang… - arXiv preprint …, 2024 - generative-vision.github.io
While novel view synthesis (NVS) has made substantial progress in 3D computer vision, it
typically requires an initial estimation of camera intrinsics and extrinsics from dense …

Viewcrafter: Taming video diffusion models for high-fidelity novel view synthesis

W Yu, J Xing, L Yuan, W Hu, X Li, Z Huang… - arXiv preprint arXiv …, 2024 - arxiv.org
Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-
view captures restricts their broader applicability. In this work, we propose\textbf …

Megascenes: Scene-level view synthesis at scale

J Tung, G Chou, R Cai, G Yang, K Zhang… - … on Computer Vision, 2025 - Springer
Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics
applications. Recently, pose-conditioned diffusion models have led to significant progress …

Compgs: Smaller and faster gaussian splatting with vector quantization

KL Navaneet, K Pourahmadi Meibodi… - … on Computer Vision, 2025 - Springer
Abstract 3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D
radiance fields that achieves much faster learning and rendering time compared to SOTA …

No pose, no problem: Surprisingly simple 3d gaussian splats from sparse unposed images

B Ye, S Liu, H Xu, X Li, M Pollefeys, MH Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes
parameterized by 3D Gaussians from\textit {unposed} sparse multi-view images. Our model …

Mvsplat360: Feed-forward 360 scene synthesis from sparse views

Y Chen, C Zheng, H Xu, B Zhuang, A Vedaldi… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce MVSplat360, a feed-forward approach for 360 {\deg} novel view synthesis
(NVS) of diverse real-world scenes, using only sparse observations. This setting is …

3dgs-enhancer: Enhancing unbounded 3d gaussian splatting with view-consistent 2d diffusion priors

X Liu, C Zhou, S Huang - arXiv preprint arXiv:2410.16266, 2024 - arxiv.org
Novel-view synthesis aims to generate novel views of a scene from multiple input images or
videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable …

Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion

W Sun, S Chen, F Liu, Z Chen, Y Duan, J Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we introduce\textbf {DimensionX}, a framework designed to generate
photorealistic 3D and 4D scenes from just a single image with video diffusion. Our approach …

AnimateAnything: Consistent and Controllable Animation for Video Generation

G Lei, C Wang, H Li, R Zhang, Y Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
We present a unified controllable video generation approach AnimateAnything that
facilitates precise and consistent video manipulation across various conditions, including …

Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning

H Zhu, Y Wang, D Huang, W Ye, W Ouyang… - arXiv preprint arXiv …, 2024 - arxiv.org
In this study, we explore the influence of different observation spaces on robot learning,
focusing on three predominant modalities: RGB, RGB-D, and point cloud. Through extensive …