Cover Image

Class-Partitioned VQ-VAE and Latent Flow Matching for Point Cloud Scene Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Edirimuni, Dasith de Silva, Mian, Ajmal Saeed
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

Hybrid Long and Short Range Flows for Point Cloud Filtering
by: Edirimuni, Dasith de Silva, et al.
Published: (2025)

Retrieving Objects from 3D Scenes with Box-Guided Open-Vocabulary Instance Segmentation
by: Nguyen, Khanh, et al.
Published: (2025)

RI-Mamba: Rotation-Invariant Mamba for Robust Text-to-Shape Retrieval
by: Nguyen, Khanh, et al.
Published: (2026)

StraightPCF: Straight Point Cloud Filtering
by: Edirimuni, Dasith de Silva, et al.
Published: (2024)

Deep Point Cloud Normal Estimation via Triplet Learning
by: Wang, Weijia, et al.
Published: (2021)

A Survey of Deep Learning-based Point Cloud Denoising
by: Wang, Jinxi, et al.
Published: (2025)

FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds
by: Zhang, Xiaoge, et al.
Published: (2025)

Diffusion Masked Pretraining for Dynamic Point Cloud
by: Zhang, Zhuoyue, et al.
Published: (2026)

Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models
by: Guo, Zihao, et al.
Published: (2026)

PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation
by: He, Yong, et al.
Published: (2025)

Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition
by: Nguyen, Khanh, et al.
Published: (2025)

Automated Road Extraction and Centreline Fitting in LiDAR Point Clouds
by: Wang, Xinyu, et al.
Published: (2025)

DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Clouds
by: Zhang, Xiaoge, et al.
Published: (2024)

Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
by: Geng, Zichen, et al.
Published: (2026)

Sparse Points to Dense Clouds: Enhancing 3D Detection with Limited LiDAR Data
by: Kumar, Aakash, et al.
Published: (2024)

Attentive VQ-VAE
by: Hoyos, Angello, et al.
Published: (2023)

Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes
by: Ibrahim, Muhammad, et al.
Published: (2025)

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
by: Jia, Mingkai, et al.
Published: (2025)

Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion
by: Liang, Li, et al.
Published: (2025)

Quantize-then-Rectify: Efficient VQ-VAE Training
by: Zhang, Borui, et al.
Published: (2025)

Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility
by: Hao, Yutong, et al.
Published: (2025)

3D Object Detection from Point Cloud via Voting Step Diffusion
by: Hou, Haoran, et al.
Published: (2024)

Exploring VQ-VAE with Prosody Parameters for Speaker Anonymization
by: Leang, Sotheara, et al.
Published: (2024)

UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes
by: Geng, Zichen, et al.
Published: (2025)

Flow AM: Generating Point Cloud Global Explanations by Latent Alignment
by: Tan, Hanxiao
Published: (2024)

ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation
by: Geng, Zichen, et al.
Published: (2025)

Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsampling
by: He, Yong, et al.
Published: (2024)

Toward Scalable, Flexible Scene Flow for Point Clouds
by: Vedder, Kyle
Published: (2025)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
by: Liang, Li, et al.
Published: (2025)

Geo-Registration of Terrestrial LiDAR Point Clouds with Satellite Images without GNSS
by: Wang, Xinyu, et al.
Published: (2025)

External Knowledge Enhanced 3D Scene Generation from Sketch
by: Wu, Zijie, et al.
Published: (2024)

Auto-Regressive Diffusion for Generating 3D Human-Object Interactions
by: Geng, Zichen, et al.
Published: (2025)

Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors
by: Wei, Hao, et al.
Published: (2026)

Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression
by: Wei, Hao, et al.
Published: (2026)

Learning Coherent Matrixized Representation in Latent Space for Volumetric 4D Generation
by: Yang, Qitong, et al.
Published: (2024)

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation
by: Lin, Min, et al.
Published: (2024)

VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization
by: Zhou, Yixuan, et al.
Published: (2024)

PUFM++: Point Cloud Upsampling via Enhanced Flow Matching
by: Liu, Zhi-Song, et al.
Published: (2025)

Multiview Point Cloud Registration Based on Minimum Potential Energy for Free-Form Blade Measurement
by: Wu, Zijie, et al.
Published: (2025)

Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
by: Vice, Jordan, et al.
Published: (2024)