arXiv Machine Learning
EMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusion
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Sep 23
Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity
Point Diffusion Mamba (PDM) is a new method that fuses diffusion models with state‑space modeling to perform single‑view 3D reconstruction when training data are scarce. It uses a lightweight reconstruction module for unordered point‑clouds, a Local Geometric Aggregation module combined with Mamba blocks to capture both global geometry and local detail, and a Hierarchical Feature Integration Network to merge high‑level semantic and local geometric features for each point. A Dynamic Weighted Sampling strategy further improves reconstruction quality by integrating generative priors, and experiments on ShapeNet and Pix3D show that PDM outperforms existing state‑of‑the‑art approaches.
arXiv Computer Vision
Oct 28
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
VolFill is a generative framework that reconstructs the complete 3D geometry of a scene from a single RGB image, addressing the challenge of inferring hidden structures. It uses a hybrid 3D VAE to encode sparse truncated unsigned distance function grids into a latent space, and a latent Diffusion Transformer to denoise and recover the full scene. By conditioning on a geometry foundation model, VolFill leverages spatial priors and provides a structured representation that enables direct surface extraction and scalable occupancy queries, outperforming existing amodal baselines on SCRREAM and NRGB-D datasets.
arXiv Computer Vision
Oct 21
TokenFlow: Latent Token Rectified Flow Matching for 3D Point Cloud Generation
arXiv:2610.27418v1 Announce Type: new Abstract: 3D point clouds generation requires capturing both part-level layout and surface detail while preserving permutation equivariance. Existing latent gene...
arXiv Computer Vision
Oct 22
Register Anything Model for Generalizable and Robust Point Cloud Registration
The paper introduces the Register Anything Model (RAM), a unified approach for 3D point cloud registration that can robustly estimate 6‑DoF transformations across a wide range of domains, including indoor, outdoor, and object scenes. RAM overcomes domain‑specific challenges by employing a geometry‑aware normalization that voxelizes and standardizes point clouds based on their geometric properties, followed by a hierarchical coarse‑to‑fine pipeline with a geometric transformer that focuses on local consistency. Experiments on 12 benchmarks show that RAM achieves state‑of‑the‑art inlier ratios and registration recall, outperforming methods trained on individual domains and demonstrating strong generalization.
arXiv Computer Vision
Sep 10
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
arXiv:2605.12957v2 Announce Type: replace Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
arXiv Computer Vision
Oct 23
GraphCAD: Geometry-Aware Diffusion on Edge-Adjacency Graphs for CAD Generation
GraphCAD introduces a geometry-aware generative framework for Computer-Aided Design (CAD) that models CAD construction using an Edge-Adjacency Graph (EAG), a novel graph-based representation. The method employs a hybrid graph diffusion process to jointly capture discrete topological connectivity and continuous spatial geometry, and incorporates a geometry-aware denoising mechanism that maps node attributes to SE(3)-equivariant encoded point sets. Experiments on the newly created EAGBench dataset demonstrate that GraphCAD can generate complex CAD models with more than 50 faces, achieving state‑of‑the‑art geometric fidelity and distributional alignment compared to sequence‑based baselines.