Pith. sign in

REVIEW 13 cited by

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Not yet reviewed by Pith; the record is open.

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 2503.21732 v1 pith:IL5EIAS5 submitted 2025-03-27 cs.CV

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

classification cs.CV
keywords high-resolutionreconstructionrenderingshapesparseflexgenerationmeshmodeling
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertight conversion, while other approaches struggle with high resolutions. This paper introduces SparseFlex, a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $1024^3$ directly from rendering losses. SparseFlex combines the accuracy of Flexicubes with a sparse voxel structure, focusing computation on surface-adjacent regions and efficiently handling open surfaces. Crucially, we introduce a frustum-aware sectional voxel training strategy that activates only relevant voxels during rendering, dramatically reducing memory consumption and enabling high-resolution training. This also allows, for the first time, the reconstruction of mesh interiors using only rendering supervision. Building upon this, we demonstrate a complete shape modeling pipeline by training a variational autoencoder (VAE) and a rectified flow transformer for high-quality 3D shape generation. Our experiments show state-of-the-art reconstruction accuracy, with a ~82% reduction in Chamfer Distance and a ~88% increase in F-score compared to previous methods, and demonstrate the generation of high-resolution, detailed 3D shapes with arbitrary topology. By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling.

discussion (0)

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

Forward citations

Cited by 13 Pith papers

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

  1. EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning

    cs.CV 2026-07 conditional novelty 6.0

    An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.

  2. Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models

    cs.CV 2026-07 unverdicted novelty 6.0

    Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.

  3. HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors

    cs.CV 2026-06 unverdicted novelty 6.0

    HiFiVe is a training-free framework using an auto-regressive texture refinement pipeline with depth-based warping, multi-view fusion, and symmetry to enhance both texture and geometry fidelity in vehicle generation fr...

  4. Pixal3D: Pixel-Aligned 3D Generation from Images

    cs.CV 2026-05 unverdicted novelty 6.0

    Pixal3D performs pixel-aligned 3D generation from images via back-projected multi-scale feature volumes, achieving fidelity close to reconstruction while supporting multi-view and scene synthesis.

  5. FusionBERT: Multi-View Image-3D Retrieval via Cross-Attention Visual Fusion and Normal-Aware 3D Encoder

    cs.CV 2026-04 unverdicted novelty 6.0

    FusionBERT uses cross-attention to fuse multi-view images and a normal-aware encoder for 3D models, achieving higher image-3D retrieval accuracy than prior multimodal models in both single- and multi-view settings.

  6. UniRecGen: Unifying Multi-View 3D Reconstruction and Generation

    cs.CV 2026-04 unverdicted novelty 6.0

    UniRecGen unifies reconstruction and generation via shared canonical space and disentangled cooperative learning to produce complete, consistent 3D models from sparse views.

  7. Native and Compact Structured Latents for 3D Generation

    cs.CV 2025-12 unverdicted novelty 6.0

    Introduces O-Voxel omni-voxel representation and Sparse Compression VAE for structured native 3D latents, enabling efficient training of large flow-matching models that produce higher-quality geometry and materials th...

  8. HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors

    cs.CV 2026-06 unverdicted novelty 5.0

    HiFiVe generates high-fidelity 3D vehicles by anchoring auto-regressive 2D texture synthesis to coarse geometry via depth warping and symmetry, then refining mesh with normal maps.

  9. ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    ISAP-3D proposes identity-slot aligned modeling with semantic identity tokens and one-to-one layout prediction to achieve stable part-aware 3D generation.

  10. MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    MeshWeaver uses sparse-voxel guidance for autoregressive surface weaving to achieve 18% compression and generate up to 16K-face meshes with improved fidelity.

  11. SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation

    cs.CV 2026-05 unverdicted novelty 5.0

    SuperVoxelGPT creates shape-adaptive, deterministically ordered supervoxel tokens via saliency-guided CVT, cutting sequence length to 12.8% of uniform voxels while claiming SOTA quality and 10x speedup on Trellis-500K.

  12. DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation

    cs.CV 2025-09 unverdicted novelty 5.0

    LGAA is a modular adapter framework that lifts multi-view diffusion models to produce 2D Gaussian Splats with PBR channels for high-quality relightable 3D mesh extraction using data-efficient finetuning on 69k instances.

  13. AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation

    cs.CV 2026-04 unverdicted novelty 4.0

    AnimateAnyMesh++ animates arbitrary 3D meshes from text using an expanded 300K-identity DyMesh-XL dataset, a power-law topology-aware DyMeshVAE-Flex, and a variable-length rectified-flow generator to produce semantica...