PoI: A Filter to Extract Pixel of Interest from Novel Views for Scene Coordinate Regression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Feifei, Song, Qi, Zhang, Chi, Shuai, Hui, Huang, Rui
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

Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction
by: Li, Feifei, et al.
Published: (2026)

Improving Hierarchical Representations of Vectorized HD Maps with Perspective Clues
by: Zhang, Chi, et al.
Published: (2024)

Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labels
by: Zhang, Qi, et al.
Published: (2025)

Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting
by: Zhang, Qi, et al.
Published: (2024)

Reprojection Errors as Prompts for Efficient Scene Coordinate Regression
by: Liu, Ting-Ru, et al.
Published: (2024)

Novel View Synthesis with Pixel-Space Diffusion Models
by: Elata, Noam, et al.
Published: (2024)

C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction
by: Huang, Kuan Wei, et al.
Published: (2025)

SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
by: Chen, Weiliang, et al.
Published: (2025)

OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
by: Engelmann, Francis, et al.
Published: (2024)

PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest
by: Deng, Jiajun, et al.
Published: (2024)

Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes
by: Zhang, Qi, et al.
Published: (2026)

WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration
by: Ni, Chaojun, et al.
Published: (2025)

FARMER: Flow AutoRegressive Transformer over Pixels
by: Zheng, Guangting, et al.
Published: (2025)

Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors
by: Nguyen, Son Tung, et al.
Published: (2025)

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
by: Zhang, Qi, et al.
Published: (2024)

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
by: Lu, Ruijie, et al.
Published: (2024)

Geometry-Aware Scene Configurations for Novel View Synthesis
by: Kim, Minkwan, et al.
Published: (2025)

Leveraging Neural Radiance Field in Descriptor Synthesis for Keypoints Scene Coordinate Regression
by: Bui, Huy-Hoang, et al.
Published: (2024)

See360: Novel Panoramic View Interpolation
by: Liu, Zhi-Song, et al.
Published: (2024)

RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes
by: Zhang, Jiarui, et al.
Published: (2025)

Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Information
by: Xu, Kuan, et al.
Published: (2024)

RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
by: Xu, Youcan, et al.
Published: (2026)

ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training
by: Bruns, Leonard, et al.
Published: (2025)

A-SCoRe: Attention-based Scene Coordinate Regression for wide-ranging scenarios
by: Bui, Huy-Hoang, et al.
Published: (2025)

EEPNet-V2: Patch-to-Pixel Solution for Efficient Cross-Modal Registration between LiDAR Point Cloud and Camera Image
by: Yue, Yuanchao, et al.
Published: (2025)

Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
by: Chen, Junyi, et al.
Published: (2024)

G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images
by: Huang, Zixiong, et al.
Published: (2024)

BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting
by: Wu, Yongchang, et al.
Published: (2025)

Text-Pass Filter: An Efficient Scene Text Detector
by: Yang, Chuang, et al.
Published: (2026)

OrbitNVS: Harnessing Video Diffusion Priors for Novel View Synthesis
by: Liang, Jinglin, et al.
Published: (2026)

DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing
by: Chi, Yufeng, et al.
Published: (2025)

R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
by: Jiang, Xudong, et al.
Published: (2025)

GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views
by: Zhou, Boyao, et al.
Published: (2024)

Recovering Parametric Scenes from Very Few Time-of-Flight Pixels
by: Sifferman, Carter, et al.
Published: (2025)

Visual Instruction Tuning with Chain of Region-of-Interest
by: Chen, Yixin, et al.
Published: (2025)

Divide and Conquer: Improving Multi-Camera 3D Perception with 2D Semantic-Depth Priors and Input-Dependent Queries
by: Song, Qi, et al.
Published: (2024)

AnyView: Synthesizing Any Novel View in Dynamic Scenes
by: Van Hoorick, Basile, et al.
Published: (2026)

From Image- to Pixel-level: Label-efficient Hyperspectral Image Reconstruction
by: Leng, Yihong, et al.
Published: (2025)

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
by: Zheng, Shunyuan, et al.
Published: (2023)

MegaScenes: Scene-Level View Synthesis at Scale
by: Tung, Joseph, et al.
Published: (2024)