Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	de Almeida, Melonie, Ivanova, Daniela, Shi, Tong, Williamson, John H., Henderson, Paul
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models
by: Henderson, Paul, et al.
Published: (2024)

Splat-Portrait: Generalizing Talking Heads with Gaussian Splatting
by: Shi, Tong, et al.
Published: (2026)

Neural 3D Reconstruction of Planetary Surfaces from Descent-Phase Wide-Angle Imagery
by: de Almeida, Melonie, et al.
Published: (2026)

Unsupervised Segmentation by Diffusing, Walking and Cutting
by: Ivanova, Daniela, et al.
Published: (2024)

ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage
by: Ivanova, Daniela, et al.
Published: (2024)

State-of-the-Art Fails in the Art of Damage Detection
by: Ivanova, Daniela, et al.
Published: (2024)

Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting
by: Zhang, Zheng, et al.
Published: (2024)

CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
by: Xu, Dejia, et al.
Published: (2024)

Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control
by: Song, Chenxi, et al.
Published: (2025)

4C4D: 4 Camera 4D Gaussian Splatting
by: Zhou, Junsheng, et al.
Published: (2026)

Pixal3D: Pixel-Aligned 3D Generation from Images
by: Li, Dong-Yang, et al.
Published: (2026)

Light-X: Generative 4D Video Rendering with Camera and Illumination Control
by: Liu, Tianqi, et al.
Published: (2025)

Beyond Inpainting: Unleash 3D Understanding for Precise Camera-Controlled Video Generation
by: Chen, Dong-Yu, et al.
Published: (2026)

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation
by: Lee, JoungBin, et al.
Published: (2025)

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
by: Wang, Yifan, et al.
Published: (2026)

AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers
by: Bahmani, Sherwin, et al.
Published: (2024)

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
by: Bahmani, Sherwin, et al.
Published: (2024)

DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
by: Li, Zhiqi, et al.
Published: (2024)

Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
by: Wang, Yikai, et al.
Published: (2024)

Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images
by: Jin, In-Hwan, et al.
Published: (2025)

Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation
by: Fu, Zhoujie, et al.
Published: (2024)

Explore the LiDAR-Camera Dynamic Adjustment Fusion for 3D Object Detection
by: Yang, Yiran, et al.
Published: (2024)

Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation
by: Shuai, Xincheng, et al.
Published: (2025)

Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering
by: Chen, Jieying, et al.
Published: (2026)

LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors
by: Chen, Yabo, et al.
Published: (2024)

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
by: Cao, Chenjie, et al.
Published: (2025)

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
by: Ren, Xuanchi, et al.
Published: (2025)

CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control
by: Popov, Stefan, et al.
Published: (2025)

LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians
by: Wu, Jiamin, et al.
Published: (2024)

GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking
by: Bian, Weikang, et al.
Published: (2025)

Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation
by: Li, Jiusi, et al.
Published: (2025)

Camera Pose Refinement via 3D Gaussian Splatting
by: Hao, Lulu, et al.
Published: (2025)

PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting
by: Miao, Qiaowei, et al.
Published: (2024)

CameraCtrl: Enabling Camera Control for Text-to-Video Generation
by: He, Hao, et al.
Published: (2024)

OneTo3D: One Image to Re-editable Dynamic 3D Model and Video Generation
by: Lin, Jinwei
Published: (2024)

GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation
by: Tao, Ye, et al.
Published: (2025)

AGG: Amortized Generative 3D Gaussians for Single Image to 3D
by: Xu, Dejia, et al.
Published: (2024)

ZFusion: An Effective Fuser of Camera and 4D Radar for 3D Object Perception in Autonomous Driving
by: Yang, Sheng, et al.
Published: (2025)

ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models
by: Wang, Xinliang, et al.
Published: (2026)

Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
by: Liu, Xiaoyan, et al.
Published: (2025)