Cover Image

Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Feng, Guo, Wenkai, Cao, Pu, Zhang, Zhicheng, Yin, Jianqin
Format:	Preprint
Published:	2025
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

Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation
by: Zhou, Feng, et al.
Published: (2025)

Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors
by: Guo, Lanqing, et al.
Published: (2025)

OMEGAS: Object Mesh Extraction from Large Scenes Guided by Gaussian Segmentation
by: Wang, Lizhi, et al.
Published: (2024)

BiTAA: A Bi-Task Adversarial Attack for Object Detection and Depth Estimation via 3D Gaussian Splatting
by: Zhang, Yixun, et al.
Published: (2025)

Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views
by: Wu, Jiang, et al.
Published: (2025)

ResDiT: Evoking the Intrinsic Resolution Scalability in Diffusion Transformers
by: Ma, Yiyang, et al.
Published: (2025)

Pi-GS: Sparse-View Gaussian Splatting with Dense π^3 Initialization
by: Hofer, Manuel, et al.
Published: (2026)

RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
by: Cheng, Chong, et al.
Published: (2025)

A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition
by: Zhang, Shaojie, et al.
Published: (2023)

Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction
by: Liu, Xinhang, et al.
Published: (2023)

Improving Geometry in Sparse-View 3DGS via Reprojection-based DoF Separation
by: Kim, Yongsung, et al.
Published: (2024)

Segmentation-Driven Initialization for Sparse-view 3D Gaussian Splatting
by: Li, Yi-Hsin, et al.
Published: (2025)

Physics-constrained Attack against Convolution-based Human Motion Prediction
by: Duan, Chengxu, et al.
Published: (2023)

TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
by: Kim, Hyeseong, et al.
Published: (2026)

Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud
by: Takama, Natsuki, et al.
Published: (2025)

ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality
by: Xu, Guoliang, et al.
Published: (2024)

L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation
by: Xu, Guoliang, et al.
Published: (2025)

Towards more realistic human motion prediction with attention to motion coordination
by: Ding, Pengxiang, et al.
Published: (2024)

CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering
by: Jiang, Yuanyuan, et al.
Published: (2024)

Contrastive Masked Autoencoders are Stronger Vision Learners
by: Huang, Zhicheng, et al.
Published: (2022)

CMIP-CIL: A Cross-Modal Benchmark for Image-Point Class Incremental Learning
by: Qi, Chao, et al.
Published: (2025)

An Initial Study of Bird's-Eye View Generation for Autonomous Vehicles using Cross-View Transformers
by: Santos, Felipe Carlos dos, et al.
Published: (2025)

A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition
by: Yin, Ruoqi, et al.
Published: (2023)

Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene Reconstruction
by: Shi, Changyue, et al.
Published: (2025)

3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving
by: Zhang, Yixun, et al.
Published: (2025)

Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
by: Jin, Xin, et al.
Published: (2024)

MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation
by: Wei, Wei, et al.
Published: (2025)

Learning Hierarchical Sparse Transform Coding for 3DGS Compression
by: Xu, Hao, et al.
Published: (2025)

CAT-3DGS Pro: A New Benchmark for Efficient 3DGS Compression
by: Zhan, Yu-Ting, et al.
Published: (2025)

PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems
by: Wang, Weijie, et al.
Published: (2026)

3D Gaussian Splatting with Fisheye Images: Field of View Analysis and Depth-Based Initialization
by: Gunes, Ulas, et al.
Published: (2025)

ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images
by: Zhang, Xiaoshuai, et al.
Published: (2024)

LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-timestamp 3D Human Pose Estimation
by: Pan, Zhiyu, et al.
Published: (2023)

Optimal Eye Surgeon: Finding Image Priors through Sparse Generators at Initialization
by: Ghosh, Avrajit, et al.
Published: (2024)

Controllable Generation with Text-to-Image Diffusion Models: A Survey
by: Cao, Pu, et al.
Published: (2024)

A General Framework to Boost 3D GS Initialization for Text-to-3D Generation by Lexical Richness
by: Jiang, Lutao, et al.
Published: (2024)

Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking
by: Van Ma, Linh, et al.
Published: (2024)

Accurate Point Measurement in 3DGS -- A New Alternative to Traditional Stereoscopic-View Based Measurements
by: Deng, Deyan, et al.
Published: (2026)

Extreme Views: 3DGS Filter for Novel View Synthesis from Out-of-Distribution Camera Poses
by: Bowness, Damian, et al.
Published: (2025)

SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition
by: Zhang, Shaojie, et al.
Published: (2023)