Image de couverture de livre

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Xingyu, Chen, Yue, Xiu, Yuliang, Geiger, Andreas, Chen, Anpei
Format:	Preprint
Publié:	2025
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

TTT3R: 3D Reconstruction as Test-Time Training
par: Chen, Xingyu, et autres
Publié: (2025)

Human3R: Everyone Everywhere All at Once
par: Chen, Yue, et autres
Publié: (2025)

$R^3$: 3D Reconstruction via Relative Regression
par: Xu, Congrong, et autres
Publié: (2026)

DUSt3R: Geometric 3D Vision Made Easy
par: Wang, Shuzhe, et autres
Publié: (2023)

Feat2GS: Probing Visual Foundation Models with Gaussian Splatting
par: Chen, Yue, et autres
Publié: (2024)

Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis
par: Chen, Hongyuan, et autres
Publié: (2026)

NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis
par: You, Zinuo, et autres
Publié: (2023)

An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks
par: Wu, Xinyi, et autres
Publié: (2025)

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs
par: Gao, Gege, et autres
Publié: (2023)

Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT
par: Zhang, Wei, et autres
Publié: (2025)

ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitives
par: Baranowski, Bartłomiej, et autres
Publié: (2025)

2D Gaussian Splatting for Geometrically Accurate Radiance Fields
par: Huang, Binbin, et autres
Publié: (2024)

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
par: Tang, Zhenggang, et autres
Publié: (2024)

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
par: Itkin, Roni, et autres
Publié: (2026)

GenFusion: Closing the Loop between Reconstruction and Generation via Videos
par: Wu, Sibo, et autres
Publié: (2025)

LaRa: Efficient Large-Baseline Radiance Fields
par: Chen, Anpei, et autres
Publié: (2024)

Spectral Probing of Feature Upsamplers in 2D-to-3D Scene Reconstruction
par: Xiao, Ling, et autres
Publié: (2026)

GaussiAnimate: Reconstruct and Rig Animatable Categories with Level of Dynamics
par: Wang, Jiaxin, et autres
Publié: (2026)

MuRF: Multi-Baseline Radiance Fields
par: Xu, Haofei, et autres
Publié: (2023)

Text-driven Human Motion Generation with Motion Masked Diffusion Model
par: Chen, Xingyu
Publié: (2024)

Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training
par: Song, Xingyu, et autres
Publié: (2024)

LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models
par: Huang, Haiwen, et autres
Publié: (2025)

DiMeR: Disentangled Mesh Reconstruction Model
par: Jiang, Lutao, et autres
Publié: (2025)

Unimotion: Unifying 3D Human Motion Synthesis and Understanding
par: Li, Chuqiao, et autres
Publié: (2024)

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

Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
par: Li, Xiao, et autres
Publié: (2025)

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering
par: You, Zinuo, et autres
Publié: (2025)

EasySplat: View-Adaptive Learning makes 3D Gaussian Splatting Easy
par: Gao, Ao, et autres
Publié: (2025)

MUT3R: Motion-aware Updating Transformer for Dynamic 3D Reconstruction
par: Shen, Guole, et autres
Publié: (2025)

Dark3R: Learning Structure from Motion in the Dark
par: Guo, Andrew Y, et autres
Publié: (2026)

Dens3R: A Foundation Model for 3D Geometry Prediction
par: Fang, Xianze, et autres
Publié: (2025)

FrankenMotion: Part-level Human Motion Generation and Composition
par: Li, Chuqiao, et autres
Publié: (2026)

LISO: Lidar-only Self-Supervised 3D Object Detection
par: Baur, Stefan, et autres
Publié: (2024)

Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image
par: Chen, Jerred, et autres
Publié: (2025)

LONG3R: Long Sequence Streaming 3D Reconstruction
par: Chen, Zhuoguang, et autres
Publié: (2025)

Absolute Coordinates Make Motion Generation Easy
par: Meng, Zichong, et autres
Publié: (2025)

STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
par: Lan, Yushi, et autres
Publié: (2025)

DisMo: Disentangled Motion Representations for Open-World Motion Transfer
par: Ressler-Antal, Thomas, et autres
Publié: (2025)

Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences
par: Li, Bao, et autres
Publié: (2026)

SAB3R: Semantic-Augmented Backbone in 3D Reconstruction
par: Chen, Xuweiyi, et autres
Publié: (2025)