Copertina

Stronger Semantic Encoders Can Harm Relighting Performance: Probing Visual Priors via Augmented Latent Intrinsics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xing, Xiaoyan, Zhang, Xiao, Karaoglu, Sezer, Gevers, Theo, Bhattad, Anand
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting
di: Xing, Xiaoyan, et al.
Pubblicazione: (2024)

Intrinsic Image Decomposition Using Point Cloud Representation
di: Xing, Xiaoyan, et al.
Pubblicazione: (2023)

Grab-3D: Detecting AI-Generated Videos from 3D Geometric Temporal Consistency
di: Chen, Wenhan, et al.
Pubblicazione: (2025)

Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction
di: Yin, Ruihong, et al.
Pubblicazione: (2024)

GaussianBlender: Instant Stylization of 3D Gaussians with Disentangled Latent Spaces
di: Ocal, Melis, et al.
Pubblicazione: (2025)

Latent Intrinsics Emerge from Training to Relight
di: Zhang, Xiao, et al.
Pubblicazione: (2024)

Ray-Distance Volume Rendering for Neural Scene Reconstruction
di: Yin, Ruihong, et al.
Pubblicazione: (2024)

Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory
di: Xing, Xiaoyan, et al.
Pubblicazione: (2024)

RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models
di: Öcal, Başak Melis, et al.
Pubblicazione: (2024)

SceneTeller: Language-to-3D Scene Generation
di: Öcal, Başak Melis, et al.
Pubblicazione: (2024)

FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
di: Yin, Ruihong, et al.
Pubblicazione: (2024)

Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
di: Zhang, Qi, et al.
Pubblicazione: (2026)

ScribbleLight: Single Image Indoor Relighting with Scribbles
di: Choi, Jun Myeong, et al.
Pubblicazione: (2024)

SpotLight: Shadow-Guided Object Relighting via Diffusion
di: Fortier-Chouinard, Frédéric, et al.
Pubblicazione: (2024)

SyncLight: Single-Edit Multi-View Relighting
di: Serrano-Lozano, David, et al.
Pubblicazione: (2026)

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
di: Bhattad, Anand, et al.
Pubblicazione: (2025)

ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion
di: Zhang, Zitian, et al.
Pubblicazione: (2024)

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion
di: Fan, Xiang, et al.
Pubblicazione: (2024)

AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priors
di: Mishra, Rameshwar, et al.
Pubblicazione: (2026)

Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance
di: Che, Quang-Huy, et al.
Pubblicazione: (2024)

PIXLRelight: Controllable Relighting via Intrinsic Conditioning
di: Farinha, Miguel, et al.
Pubblicazione: (2026)

Modeling Weather Uncertainty for Multi-weather Co-Presence Estimation
di: Bi, Qi, et al.
Pubblicazione: (2024)

Learning Relighting and Intrinsic Decomposition in Neural Radiance Fields
di: Yang, Yixiong, et al.
Pubblicazione: (2024)

Relightable Neural Actor with Intrinsic Decomposition and Pose Control
di: Luvizon, Diogo, et al.
Pubblicazione: (2023)

Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics
di: Liu, Jipeng, et al.
Pubblicazione: (2026)

SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
di: Li, Deming, et al.
Pubblicazione: (2026)

Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction
di: Yin, Ruihong, et al.
Pubblicazione: (2025)

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

FVO: Fast Visual Odometry with Transformers
di: Yugay, Vlardimir, et al.
Pubblicazione: (2025)

Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering
di: Li, Ao, et al.
Pubblicazione: (2026)

SGDM: Static-Guided Dynamic Module Make Stronger Visual Models
di: Xing, Wenjie, et al.
Pubblicazione: (2024)

MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM
di: Yugay, Vladimir, et al.
Pubblicazione: (2024)

Learning Latent Proxies for Controllable Single-Image Relighting
di: Zheng, Haoze, et al.
Pubblicazione: (2026)

Optimal Sample Lens Positioning in Digital Camera Systems
di: Karaoglu, Ali
Pubblicazione: (2024)

Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views
di: Singh, Kunwar Maheep, et al.
Pubblicazione: (2025)

Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecture
di: Yang, Yixiong, et al.
Pubblicazione: (2024)

Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
di: Yugay, Vladimir, et al.
Pubblicazione: (2023)

T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning
di: Wei, Weijie, et al.
Pubblicazione: (2023)

Synthetic Perception: Can Generated Images Unlock Latent Visual Prior for Text-Centric Reasoning?
di: Huang, Yuesheng, et al.
Pubblicazione: (2025)

Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
di: Thozhiyoor, Varun Varma, et al.
Pubblicazione: (2025)