Pith. sign in

REVIEW 6 cited by

3D Shape Tokenization via Latent Flow Matching

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.15618 v3 pith:6QX5EO66 submitted 2024-12-20 cs.CV cs.GR

3D Shape Tokenization via Latent Flow Matching

Jen-Hao Rick Chang , Yuyang Wang , Miguel Angel Bautista Martin , Jiatao Gu , Xiaoming Zhao , Josh Susskind , Oncel Tuzel This is my paper
classification cs.CV cs.GR
keywords modelsdataestimationflowgenerativeincludinglatentlearning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a latent 3D representation that models 3D surfaces as probability density functions in 3D, i.e., p(x,y,z), with flow-matching. Our representation is specifically designed for consumption by machine learning models, offering continuity and compactness by construction while requiring only point clouds and minimal data preprocessing. Despite being a data-driven method, our use of flow matching in the 3D space enables interesting geometry properties, including the capabilities to perform zero-shot estimation of surface normal and deformation field. We evaluate with several machine learning tasks, including 3D-CLIP, unconditional generative models, single-image conditioned generative model, and intersection-point estimation. Across all experiments, our models achieve competitive performance to existing baselines, while requiring less preprocessing and auxiliary information from training data.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Generative Modeling with Orbit-Space Particle Flow Matching

    cs.GR 2026-05 unverdicted novelty 7.0

    OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.

  2. Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors

    cs.CV 2026-04 unverdicted novelty 7.0

    A video generation approach conditions a base model with multi-scale 3D latent features and a cross-attention adapter to produce geometrically realistic and consistent orbital videos from one image.

  3. ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

    cs.CV 2026-07 unverdicted novelty 6.0

    ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.

  4. DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

    cs.CV 2026-06 unverdicted novelty 6.0

    DynaTok introduces a token-based framework for correspondence-free 4D reconstruction from partial point cloud sequences via latent encoding, transformer aggregation, residual decoupling, and flow-matching decoding.

  5. Generative 3D Gaussians with Learned Density Control

    cs.GR 2026-05 unverdicted novelty 6.0

    DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.

  6. VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation

    cs.CV 2026-03 conditional novelty 6.0

    VesselTok learns compact continuous tokens of large tubular biomedical graphs from centerline points plus a fixed pseudo-radius, enabling reconstruction, generation, and link prediction across anatomies.