Cover Image

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nam, Jisu, Koo, Jahyeok, Son, Soowon, Jung, Jaewoo, An, Honggyu, Hur, Junhwa, Kim, Seungryong
Format:	Preprint
Published:	2026
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

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

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

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

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

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

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

Diffusion Model for Dense Matching
by: Nam, Jisu, et al.
Published: (2023)

AnthroTAP: Learning Point Tracking with Real-World Motion
by: Kim, Inès Hyeonsu, et al.
Published: (2025)

MATRIX: Mask Track Alignment for Interaction-aware Video Generation
by: Jin, Siyoon, et al.
Published: (2025)

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

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

Cross-View Completion Models are Zero-shot Correspondence Estimators
by: An, Honggyu, et al.
Published: (2024)

Visual Persona: Foundation Model for Full-Body Human Customization
by: Nam, Jisu, et al.
Published: (2025)

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

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
by: Yi, Jung, et al.
Published: (2025)

PLOT: Pseudo-Labeling via Video Object Tracking for Scalable Monocular 3D Object Detection
by: Lee, Seokyeong, et al.
Published: (2025)

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

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

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

CorGi: Contribution-Guided Block-Wise Interval Caching for Training-Free Acceleration of Diffusion Transformers
by: Son, Yonglak, et al.
Published: (2025)

Referring Video Object Segmentation via Language-aligned Track Selection
by: Kim, Seongchan, et al.
Published: (2024)

Exploring Temporally-Aware Features for Point Tracking
by: Kim, Inès Hyeonsu, et al.
Published: (2025)

Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation
by: Kim, Kihong, et al.
Published: (2024)

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

DELTAv2: Accelerating Dense 3D Tracking
by: Ngo, Tuan Duc, et al.
Published: (2025)

URECA: Unique Region Caption Anything
by: Lim, Sangbeom, et al.
Published: (2025)

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

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

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
by: Lu, Jiahao, et al.
Published: (2026)

Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification
by: Kim, Inès Hyeonsu, et al.
Published: (2024)

DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization
by: Nam, Jisu, et al.
Published: (2024)

Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding
by: Kim, Namho, et al.
Published: (2025)

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

AgentRVOS: Reasoning over Object Tracks for Zero-Shot Referring Video Object Segmentation
by: Jin, Woojeong, et al.
Published: (2026)

GR3EN: Generative Relighting for 3D Environments
by: Xing, Xiaoyan, et al.
Published: (2026)

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
by: Zhang, Chenshuang, et al.
Published: (2025)

Dense Matchers for Dense Tracking
by: Jelínek, Tomáš, et al.
Published: (2024)

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

3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow
by: Taubner, Felix, et al.
Published: (2024)

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation
by: Nam, Jisu, et al.
Published: (2026)