Copertina

Cross-View Completion Models are Zero-shot Correspondence Estimators

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	An, Honggyu, Kim, Jinhyeon, Park, Seonghoon, Jung, Jaewoo, Han, Jisang, Hong, Sunghwan, Kim, Seungryong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting
di: Jung, Jaewoo, et al.
Pubblicazione: (2024)

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers
di: Han, Jisang, et al.
Pubblicazione: (2025)

D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes
di: Han, Jisang, et al.
Pubblicazione: (2025)

Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs
di: Hong, Sunghwan, et al.
Pubblicazione: (2023)

PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting
di: Hong, Sunghwan, et al.
Pubblicazione: (2024)

Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters
di: Lee, Gyuseong, et al.
Pubblicazione: (2023)

Visual Representation Alignment for Multimodal Large Language Models
di: Yoon, Heeji, et al.
Pubblicazione: (2025)

C3G: Learning Compact 3D Representations with 2K Gaussians
di: An, Honggyu, et al.
Pubblicazione: (2025)

Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
di: Gröpl, Marcel, et al.
Pubblicazione: (2026)

Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
di: Kim, Mungyeom, et al.
Pubblicazione: (2026)

Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
di: Hong, Sunghwan, et al.
Pubblicazione: (2024)

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

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
di: Nam, Jisu, et al.
Pubblicazione: (2026)

Local All-Pair Correspondence for Point Tracking
di: Cho, Seokju, et al.
Pubblicazione: (2024)

DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
di: Hong, Susung, et al.
Pubblicazione: (2023)

CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models
di: Kwon, Minkyung, et al.
Pubblicazione: (2025)

TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation
di: Yang, Jini, et al.
Pubblicazione: (2026)

Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
di: Seo, Junyoung, et al.
Pubblicazione: (2025)

RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects
di: Kim, Jaeguk, et al.
Pubblicazione: (2025)

URECA: Unique Region Caption Anything
di: Lim, Sangbeom, et al.
Pubblicazione: (2025)

Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
di: Kwak, Min-Seop, et al.
Pubblicazione: (2025)

MV-TAP: Tracking Any Point in Multi-View Videos
di: Koo, Jahyeok, et al.
Pubblicazione: (2025)

EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions
di: Yoon, Taegyoon, et al.
Pubblicazione: (2026)

CORAL: Correspondence Alignment for Improved Virtual Try-On
di: Kim, Jiyoung, et al.
Pubblicazione: (2026)

Repurposing Geometric Foundation Models for Multi-view Diffusion
di: Jang, Wooseok, et al.
Pubblicazione: (2026)

Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images
di: Kim, Jiwon, et al.
Pubblicazione: (2023)

Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
di: Shin, Heeseong, et al.
Pubblicazione: (2024)

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
di: Cho, Seokju, et al.
Pubblicazione: (2023)

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
di: Kim, Chaehyun, et al.
Pubblicazione: (2025)

Emergent Temporal Correspondences from Video Diffusion Transformers
di: Nam, Jisu, et al.
Pubblicazione: (2025)

Projected Representation Conditioning for High-fidelity Novel View Synthesis
di: Kwak, Min-Seop, et al.
Pubblicazione: (2026)

Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation
di: Park, Jaewoo, et al.
Pubblicazione: (2024)

CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences
di: Kim, Seungwook, et al.
Pubblicazione: (2024)

Repurposing Video Diffusion Transformers for Robust Point Tracking
di: Son, Soowon, et al.
Pubblicazione: (2025)

ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking
di: Chen, Jianqiu, et al.
Pubblicazione: (2025)

MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation
di: Kim, Seyeon, et al.
Pubblicazione: (2024)

Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior
di: Hyoseok, Lee, et al.
Pubblicazione: (2025)

Zero-shot Vision-Language Reranking for Cross-View Geolocalization
di: Erzurumlu, Yunus Talha, et al.
Pubblicazione: (2026)

Towards Cross-View Point Correspondence in Vision-Language Models
di: Wang, Yipu, et al.
Pubblicazione: (2025)

Training-Free Refinement of Flow Matching with Divergence-based Sampling
di: Cha, Yeonwoo, et al.
Pubblicazione: (2026)