Imagen de Portada

Stream3D: Sequential Multi-View 3D Generation via Evidential Memory

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Kaichen, Bai, Zeyang, Chang, Xinhai, Wang, Mengyu, Liang, Paul, Zhan, Fangneng
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PAGE-4D: VGGT-4D Perception via Disentangled Pose and Geometry Estimation
por: Zhou, Kaichen, et al.
Publicado: (2025)

Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry
por: Chang, Xinhai, et al.
Publicado: (2024)

Abstract 3D Perception for Spatial Intelligence in Vision-Language Models
por: Liu, Yifan, et al.
Publicado: (2025)

GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
por: Zhou, Kaichen, et al.
Publicado: (2026)

MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation
por: Xu, Muyu, et al.
Publicado: (2025)

Memorization in 3D Shape Generation: An Empirical Study
por: Pu, Shu, et al.
Publicado: (2025)

DiffAge3D: Diffusion-based 3D-aware Face Aging
por: Wahid, Junaid, et al.
Publicado: (2024)

Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey
por: Zhang, Jiahui, et al.
Publicado: (2025)

SOGS: Second-Order Anchor for Advanced 3D Gaussian Splatting
por: Zhang, Jiahui, et al.
Publicado: (2025)

DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
por: Chi, Yu, et al.
Publicado: (2023)

FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization
por: Zhang, Jiahui, et al.
Publicado: (2024)

RAD: A Dataset and Benchmark for Real-Life Anomaly Detection with Robotic Observations
por: Zhou, Kaichen, et al.
Publicado: (2024)

Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction
por: Zhang, Runmin, et al.
Publicado: (2025)

StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting
por: Liu, Kunhao, et al.
Publicado: (2024)

SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting
por: Zhou, Kaichen, et al.
Publicado: (2023)

Pathformer3D: A 3D Scanpath Transformer for 360° Images
por: Quan, Rong, et al.
Publicado: (2024)

AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance
por: Xu, Tianling, et al.
Publicado: (2025)

Uncertainty Estimation for 3D Object Detection via Evidential Learning
por: Durasov, Nikita, et al.
Publicado: (2024)

MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation
por: Li, Baicheng, et al.
Publicado: (2026)

Dehallu3D: Hallucination-Mitigated 3D Generation from Single Image via Cyclic View Consistency Refinement
por: Wang, Xiwen, et al.
Publicado: (2026)

Boosting Instance Awareness via Cross-View Correlation with 4D Radar and Camera for 3D Object Detection
por: Bai, Xiaokai, et al.
Publicado: (2026)

3DPR: Single Image 3D Portrait Relight using Generative Priors
por: Rao, Pramod, et al.
Publicado: (2025)

Evidential Deep Partial Multi-View Classification With Discount Fusion
por: Huang, Haojian, et al.
Publicado: (2024)

Weakly Supervised 3D Open-vocabulary Segmentation
por: Liu, Kunhao, et al.
Publicado: (2023)

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE
por: Chen, Yongwei, et al.
Publicado: (2024)

Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior
por: Chen, Cheng, et al.
Publicado: (2024)

Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection
por: Chang, Gyusam, et al.
Publicado: (2024)

Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection
por: Kang, Xiaolu, et al.
Publicado: (2026)

ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis
por: Wang, Chuang, et al.
Publicado: (2025)

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
por: Lou, Tianrui, et al.
Publicado: (2025)

MVLight: Relightable Text-to-3D Generation via Light-conditioned Multi-View Diffusion
por: Shim, Dongseok, et al.
Publicado: (2024)

AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
por: Zhang, Xuying, et al.
Publicado: (2025)

HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View
por: Wu, Yiming, et al.
Publicado: (2023)

GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noise
por: Li, Xinhai, et al.
Publicado: (2023)

Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training
por: Liu, Changkun, et al.
Publicado: (2026)

ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers
por: Li, Jinke, et al.
Publicado: (2024)

Duoduo CLIP: Efficient 3D Understanding with Multi-View Images
por: Lee, Han-Hung, et al.
Publicado: (2024)

3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
por: Luo, Yihang, et al.
Publicado: (2024)

GeoWorld-VLM: Geometry from World Models for Vision-Language Models
por: Gu, Renjie, et al.
Publicado: (2026)

StreamME: Simplify 3D Gaussian Avatar within Live Stream
por: Song, Luchuan, et al.
Publicado: (2025)