Cover Image

Rethinking Image-to-3D Generation with Sparse Queries: Efficiency, Capacity, and Input-View Bias

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Zhiyuan, Liu, Jiuming, Chen, Yuxin, Tomizuka, Masayoshi, Xu, Chenfeng, Peng, Chensheng
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

A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
by: Peng, Chensheng, et al.
Published: (2024)

CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
by: Ge, Chongjian, et al.
Published: (2024)

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
by: Peng, Chensheng, et al.
Published: (2024)

Q-SLAM: Quadric Representations for Monocular SLAM
by: Peng, Chensheng, et al.
Published: (2024)

X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
by: Xie, Yichen, et al.
Published: (2024)

UniQueR: Unified Query-based Feedforward 3D Reconstruction
by: Peng, Chensheng, et al.
Published: (2026)

RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives
by: Zeng, Kunnong, et al.
Published: (2026)

TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection
by: Jacobson, Philip, et al.
Published: (2024)

Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control
by: Chen, Yuxin, et al.
Published: (2025)

Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
by: Li, Yiheng, et al.
Published: (2024)

Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
by: Li, Yiheng, et al.
Published: (2025)

What Matters to You? Towards Visual Representation Alignment for Robot Learning
by: Tian, Ran, et al.
Published: (2023)

Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
by: Liu, Jiuming, et al.
Published: (2026)

Looking Backward: Streaming Video-to-Video Translation with Feature Banks
by: Liang, Feng, et al.
Published: (2024)

URoPE: Universal Relative Position Embedding across Geometric Spaces
by: Xie, Yichen, et al.
Published: (2026)

Pre-training on Synthetic Driving Data for Trajectory Prediction
by: Li, Yiheng, et al.
Published: (2023)

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
by: Tian, Ran, et al.
Published: (2024)

SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
by: Dai, Chensheng, et al.
Published: (2026)

PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search
by: Peng, Chensheng, et al.
Published: (2024)

Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation
by: Wang, Yixiao, et al.
Published: (2024)

DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation
by: Zhang, Huixin, et al.
Published: (2024)

Sparse Input View Synthesis: 3D Representations and Reliable Priors
by: Somraj, Nagabhushan
Published: (2024)

RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space
by: Xie, Yichen, et al.
Published: (2026)

MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views
by: Xu, Wangze, et al.
Published: (2024)

Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
by: Sobol, Ido, et al.
Published: (2024)

R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
by: Ljungbergh, William, et al.
Published: (2025)

RoadBEV: Road Surface Reconstruction in Bird's Eye View
by: Zhao, Tong, et al.
Published: (2024)

LDGNet: A Lightweight Difference Guiding Network for Remote Sensing Change Detection
by: Xu, Chenfeng
Published: (2025)

NeRFs in Robotics: A Survey
by: Wang, Guangming, et al.
Published: (2024)

DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment
by: Liu, Jiuming, et al.
Published: (2024)

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
by: Chen, Yuedong, et al.
Published: (2024)

PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views
by: Fei, Xin, et al.
Published: (2024)

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
by: Cao, Xiao, et al.
Published: (2026)

FlexGen: Flexible Multi-View Generation from Text and Image Inputs
by: Xu, Xinli, et al.
Published: (2024)

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Aggregative Gaussian Splatting
by: Wang, Yuxin, et al.
Published: (2025)

When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIP
by: Chu, Beilin, et al.
Published: (2025)

AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
by: Liang, Xinyue, et al.
Published: (2025)

Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting
by: Sun, Xiangyu, et al.
Published: (2025)

Geometry-Consistent 4D Gaussian Splatting for Sparse-Input Dynamic View Synthesis
by: Li, Yiwei, et al.
Published: (2025)

StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation
by: Kodaira, Akio, et al.
Published: (2023)