Copertina

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Lin-Zhuo, Liu, Kangjie, Lin, Youtian, Zhu, Siyu, Li, Zhihao, Cao, Xun, Yao, Yao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing
di: Gao, Jian, et al.
Pubblicazione: (2023)

STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians
di: Zeng, Yifei, et al.
Pubblicazione: (2024)

Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
di: Wu, Shuang, et al.
Pubblicazione: (2024)

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
di: Wu, Shuang, et al.
Pubblicazione: (2025)

Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
di: Chen, Kangjie, et al.
Pubblicazione: (2025)

TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
di: Zeng, Yifei, et al.
Pubblicazione: (2025)

VeCoR -- Velocity Contrastive Regularization for Flow Matching
di: Hong, Zong-Wei, et al.
Pubblicazione: (2025)

Elite-EvGS: Learning Event-based 3D Gaussian Splatting by Distilling Event-to-Video Priors
di: Zhang, Zixin, et al.
Pubblicazione: (2024)

Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence
di: Yuan, Tianyu, et al.
Pubblicazione: (2025)

Flow-OPD: On-Policy Distillation for Flow Matching Models
di: Fang, Zhen, et al.
Pubblicazione: (2026)

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
di: Zhu, Shenhao, et al.
Pubblicazione: (2024)

Towards Native Generative Model for 3D Head Avatar
di: Zhuang, Yiyu, et al.
Pubblicazione: (2024)

UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
di: Liu, Zexiang, et al.
Pubblicazione: (2023)

Lightweight Model Pre-training via Language Guided Knowledge Distillation
di: Li, Mingsheng, et al.
Pubblicazione: (2024)

Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360°
di: He, Yuxiao, et al.
Pubblicazione: (2024)

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
di: Wang, Jiahao, et al.
Pubblicazione: (2025)

Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching
di: Lin, Yexiong, et al.
Pubblicazione: (2025)

Straighter Flow Matching via a Diffusion-Based Coupling Prior
di: Xing, Siyu, et al.
Pubblicazione: (2023)

SuperFlow: Training Flow Matching Models with RL on the Fly
di: Chen, Kaijie, et al.
Pubblicazione: (2025)

KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV
di: Chen, Zhihao, et al.
Pubblicazione: (2026)

SurgicalGaussian: Deformable 3D Gaussians for High-Fidelity Surgical Scene Reconstruction
di: Xie, Weixing, et al.
Pubblicazione: (2024)

Beyond Single-Sample: Reliable Multi-Sample Distillation for Video Understanding
di: Li, Songlin, et al.
Pubblicazione: (2026)

GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors
di: Yu, Xiqian, et al.
Pubblicazione: (2024)

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
di: Liu, Enshu, et al.
Pubblicazione: (2024)

Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting
di: Liu, Hao, et al.
Pubblicazione: (2024)

ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes
di: Gao, Jian, et al.
Pubblicazione: (2025)

Boosting Zero-Shot 3D Style Transfer with 2D Pre-trained Priors
di: Dong, Xin, et al.
Pubblicazione: (2026)

Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling
di: Kim, Hayeon, et al.
Pubblicazione: (2025)

EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head
di: He, Qianyun, et al.
Pubblicazione: (2024)

Distilled-3DGS:Distilled 3D Gaussian Splatting
di: Xiang, Lintao, et al.
Pubblicazione: (2025)

Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs
di: Zhong, Yingji, et al.
Pubblicazione: (2025)

Large-Scale 3D Medical Image Pre-training with Geometric Context Priors
di: Wu, Linshan, et al.
Pubblicazione: (2024)

Mitigating Ambiguities in 3D Classification with Gaussian Splatting
di: Zhang, Ruiqi, et al.
Pubblicazione: (2025)

FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video
di: Zhang, Jiawei, et al.
Pubblicazione: (2024)

3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
di: Liu, Xi, et al.
Pubblicazione: (2024)

HRAvatar: High-Quality and Relightable Gaussian Head Avatar
di: Zhang, Dongbin, et al.
Pubblicazione: (2025)

GaussianPro: 3D Gaussian Splatting with Progressive Propagation
di: Cheng, Kai, et al.
Pubblicazione: (2024)

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
di: Cai, Xu, et al.
Pubblicazione: (2025)

Rethinking Knowledge in Distillation: An In-context Sample Retrieval Perspective
di: Zhu, Jinjing, et al.
Pubblicazione: (2025)

I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow
di: Du, Ruoyi, et al.
Pubblicazione: (2024)