Imagen de Portada

G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kani, Bharath Raj Nagoor, Snavely, Noah
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

UpFusion: Novel View Diffusion from Unposed Sparse View Observations
por: Kani, Bharath Raj Nagoor, et al.
Publicado: (2023)

Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly
por: Chetan, Aditya, et al.
Publicado: (2026)

Learning Feature Descriptors using Camera Pose Supervision
por: Wang, Qianqian, et al.
Publicado: (2020)

Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos
por: Luo, Rundong, et al.
Publicado: (2025)

ObjectCarver: Semi-automatic segmentation, reconstruction and separation of 3D objects
por: Hassena, Gemmechu, et al.
Publicado: (2024)

KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos
por: Chou, Gene, et al.
Publicado: (2024)

Wide-Baseline Relative Camera Pose Estimation with Directional Learning
por: Chen, Kefan, et al.
Publicado: (2021)

ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild
por: Chen, Hanyu, et al.
Publicado: (2026)

Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis
por: Nguyen, Thang-Anh-Quan, et al.
Publicado: (2025)

Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
por: Cheng, Chong, et al.
Publicado: (2025)

FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution
por: Chou, Gene, et al.
Publicado: (2025)

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

Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
por: Xiangli, Yuanbo, et al.
Publicado: (2024)

Honey, I Shrunk the Arc de Triomphe!
por: Xiangli, Yuanbo, et al.
Publicado: (2026)

Generative Image Dynamics
por: Li, Zhengqi, et al.
Publicado: (2023)

Seeing a Rose in Five Thousand Ways
por: Zhang, Yunzhi, et al.
Publicado: (2022)

MV-SAM: Multi-view Promptable Segmentation using Pointmap Guidance
por: Jeong, Yoonwoo, et al.
Publicado: (2026)

Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field
por: Hu, Wenhao, et al.
Publicado: (2025)

Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding
por: Mao, Ye, et al.
Publicado: (2026)

CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
por: Chou, Gene, et al.
Publicado: (2026)

Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
por: Jin, Linyi, et al.
Publicado: (2024)

MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps
por: Lei, Jiahui, et al.
Publicado: (2025)

POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
por: Zhang, Songyan, et al.
Publicado: (2025)

ShadowDraw: From Any Object to Shadow-Drawing Compositional Art
por: Luo, Rundong, et al.
Publicado: (2025)

Long-tail Internet photo reconstruction
por: Li, Yuan, et al.
Publicado: (2026)

FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT
por: Xu, Zhisong, et al.
Publicado: (2026)

Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
por: Deng, Boyang, et al.
Publicado: (2024)

Enhancing Video Inpainting with Aligned Frame Interval Guidance
por: Xie, Ming, et al.
Publicado: (2025)

Can Generative Video Models Help Pose Estimation?
por: Cai, Ruojin, et al.
Publicado: (2024)

Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis
por: Geyer, Michal, et al.
Publicado: (2025)

Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports
por: Comandur, Bharath
Publicado: (2022)

ImageLab: Simplifying Image Processing Exploration for Novices and Experts Alike
por: Dissanayaka, Sahan, et al.
Publicado: (2024)

TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
por: Mao, Jianda, et al.
Publicado: (2025)

MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
por: Li, Zhengqi, et al.
Publicado: (2024)

FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering
por: Beisswenger, Ole, et al.
Publicado: (2025)

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
por: Zhang, Tianyuan, et al.
Publicado: (2024)

ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
por: Jin, Haian, et al.
Publicado: (2026)

Dress-Me-Up: A Dataset & Method for Self-Supervised 3D Garment Retargeting
por: Naik, Shanthika, et al.
Publicado: (2024)

SAM3-UNet: Simplified Adaptation of Segment Anything Model 3
por: Xiong, Xinyu, et al.
Publicado: (2025)