Enhancing Close-up Novel View Synthesis via Pseudo-labeling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xia, Jiatong, Sun, Libo, Liu, Lingqiao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Close-up-GS: Enhancing Close-Up View Synthesis in 3D Gaussian Splatting with Progressive Self-Training
di: Xia, Jiatong, et al.
Pubblicazione: (2025)

Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images
di: Xia, Jiatong, et al.
Pubblicazione: (2026)

Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
di: Xia, Jiatong, et al.
Pubblicazione: (2026)

SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera
di: Dai, Gaole, et al.
Pubblicazione: (2024)

Regularizing Neural Network Training via Identity-wise Discriminative Feature Suppression
di: Chapman, Avraham, et al.
Pubblicazione: (2022)

Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysis
di: Luo, Yufei, et al.
Pubblicazione: (2024)

Learning Novel View Synthesis from Heterogeneous Low-light Captures
di: Zheng, Quan, et al.
Pubblicazione: (2024)

Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
di: Wang, Zehao, et al.
Pubblicazione: (2024)

Semantic Smoothing via Novel View Synthesis for Robust SAR Image Classification
di: Brignac, Daniel, et al.
Pubblicazione: (2026)

Enhancing Fine-Grained Visual Recognition in the Low-Data Regime Through Feature Magnitude Regularization
di: Chapman, Avraham, et al.
Pubblicazione: (2024)

DT-NVS: Diffusion Transformers for Novel View Synthesis
di: Jang, Wonbong, et al.
Pubblicazione: (2025)

Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image
di: Zhang, Kaidi, et al.
Pubblicazione: (2026)

EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
di: Zhang, Yancheng, et al.
Pubblicazione: (2025)

View-Invariant Policy Learning via Zero-Shot Novel View Synthesis
di: Tian, Stephen, et al.
Pubblicazione: (2024)

Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning
di: Wu, Jiaqi, et al.
Pubblicazione: (2025)

Embedded Multi-label Feature Selection via Orthogonal Regression
di: Xu, Xueyuan, et al.
Pubblicazione: (2024)

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement
di: Wu, Hao, et al.
Pubblicazione: (2024)

A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification
di: Wu, Jiaqi, et al.
Pubblicazione: (2024)

EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection
di: Jiang, Shuo, et al.
Pubblicazione: (2026)

Pseudo Labelling for Enhanced Masked Autoencoders
di: Nandam, Srinivasa Rao, et al.
Pubblicazione: (2024)

Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition
di: Baby, Britty, et al.
Pubblicazione: (2025)

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization
di: Lan, Yuqin, et al.
Pubblicazione: (2026)

GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing
di: Wang, Yuanhao, et al.
Pubblicazione: (2025)

Aria-NeRF: Multimodal Egocentric View Synthesis
di: Sun, Jiankai, et al.
Pubblicazione: (2023)

Novel View Synthesis with Neural Radiance Fields for Industrial Robot Applications
di: Hillemann, Markus, et al.
Pubblicazione: (2024)

KARGEN: Knowledge-enhanced Automated Radiology Report Generation Using Large Language Models
di: Li, Yingshu, et al.
Pubblicazione: (2024)

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement
di: He, Xu, et al.
Pubblicazione: (2024)

Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures
di: Bühler, Marcel C., et al.
Pubblicazione: (2024)

True Self-Supervised Novel View Synthesis is Transferable
di: Mitchel, Thomas W., et al.
Pubblicazione: (2025)

SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding
di: Chen, Mingfei, et al.
Pubblicazione: (2025)

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
di: Lu, Cheng-You, et al.
Pubblicazione: (2026)

Scaling View Synthesis Transformers
di: Kim, Evan, et al.
Pubblicazione: (2026)

You Only Need One Stage: Novel-View Synthesis From A Single Blind Face Image
di: Wang, Taoyue, et al.
Pubblicazione: (2026)

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
di: Jia, Xiaosong, et al.
Pubblicazione: (2026)

HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
di: Zhou, Ziqin, et al.
Pubblicazione: (2025)

Dynamic View Synthesis as an Inverse Problem
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2025)

Boosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning
di: Huang, Gui, et al.
Pubblicazione: (2026)

Aug3D: Augmenting large scale outdoor datasets for Generalizable Novel View Synthesis
di: Rauniyar, Aditya, et al.
Pubblicazione: (2025)

Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting
di: Kumar, Raja, et al.
Pubblicazione: (2024)

Learning Neural Exposure Fields for View Synthesis
di: Niemeyer, Michael, et al.
Pubblicazione: (2025)