Image de couverture de livre

UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hur, Junhwa, Herrmann, Charles, Peng, Songyou, Henzler, Philipp, Ma, Zeyu, Zickler, Todd, Sun, Deqing
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Boundary Attention: Learning curves, corners, junctions and grouping
par: Polansky, Mia Gaia, et autres
Publié: (2024)

GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
par: Gu, Leslie, et autres
Publié: (2025)

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
par: Chen, Xiaoxue, et autres
Publié: (2025)

GR3EN: Generative Relighting for 3D Environments
par: Xing, Xiaoyan, et autres
Publié: (2026)

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
par: Zhang, Junyi, et autres
Publié: (2026)

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
par: Ye, Botao, et autres
Publié: (2024)

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
par: Zhang, Junyi, et autres
Publié: (2023)

MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
par: Zhang, Junyi, et autres
Publié: (2024)

CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
par: Chou, Gene, et autres
Publié: (2026)

Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation
par: Yin, Minghao, et autres
Publié: (2025)

LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images
par: He, Hao, et autres
Publié: (2024)

High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion
par: Hur, Junhwa, et autres
Publié: (2024)

Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes
par: Wang, Shuo, et autres
Publié: (2026)

UniSem: Generalizable Semantic 3D Reconstruction from Sparse Unposed Images
par: Liao, Guibiao, et autres
Publié: (2026)

Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views
par: Bao, Chong, et autres
Publié: (2025)

UVRM: A Scalable 3D Reconstruction Model from Unposed Videos
par: Kao, Shiu-hong, et autres
Publié: (2025)

3D Neural Edge Reconstruction
par: Li, Lei, et autres
Publié: (2024)

Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation
par: Alzayer, Hadi, et autres
Publié: (2024)

CObL: Toward Zero-Shot Ordinal Layering without User Prompting
par: Damaraju, Aneel, et autres
Publié: (2025)

WonderJourney: Going from Anywhere to Everywhere
par: Yu, Hong-Xing, et autres
Publié: (2023)

Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
par: Zhou, Bo, et autres
Publié: (2026)

4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
par: Wang, Chaoyang, et autres
Publié: (2025)

Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
par: Liu, Hongyuan, et autres
Publié: (2026)

LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
par: Kim, Jihwan, et autres
Publié: (2026)

VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression
par: Sargent, Kyle, et autres
Publié: (2025)

SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
par: Guo, Jiaxin, et autres
Publié: (2025)

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
par: Liu, Xingyu, et autres
Publié: (2024)

SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images
par: Sheng, Yu, et autres
Publié: (2025)

Large Spatial Model: End-to-end Unposed Images to Semantic 3D
par: Fan, Zhiwen, et autres
Publié: (2024)

ZeroGS: Training 3D Gaussian Splatting from Unposed Images
par: Chen, Yu, et autres
Publié: (2024)

Generative Perception of Shape and Material from Differential Motion
par: Han, Xinran Nicole, et autres
Publié: (2025)

Multistable Shape from Shading Emerges from Patch Diffusion
par: Han, Xinran Nicole, et autres
Publié: (2024)

RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting
par: Wang, Xuezhen, et autres
Publié: (2026)

Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images
par: Sun, Xiangyu, et autres
Publié: (2025)

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
par: Nam, Jisu, et autres
Publié: (2026)

On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
par: Meuleman, Andreas, et autres
Publié: (2025)

StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
par: LI, Yang, et autres
Publié: (2025)

Feedforward 3D Editing via Text-Steerable Image-to-3D
par: Ma, Ziqi, et autres
Publié: (2025)

No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
par: Balice, Matteo, et autres
Publié: (2026)

Motion Prompting: Controlling Video Generation with Motion Trajectories
par: Geng, Daniel, et autres
Publié: (2024)