Pith. sign in

REVIEW 9 cited by

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction

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 2410.06245 v1 pith:HBWUHFN2 submitted 2024-10-08 cs.CV

Shengji Tang , Weicai Ye , Peng Ye , Weihao Lin , Yang Zhou , Tao Chen , Wanli Ouyang This is my paper
classification cs.CV
keywords gaussiangaussianshisplathierarchicalgeneralizablenovelsplattingdetails
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reconstructing 3D scenes from multiple viewpoints is a fundamental task in stereo vision. Recently, advances in generalizable 3D Gaussian Splatting have enabled high-quality novel view synthesis for unseen scenes from sparse input views by feed-forward predicting per-pixel Gaussian parameters without extra optimization. However, existing methods typically generate single-scale 3D Gaussians, which lack representation of both large-scale structure and texture details, resulting in mislocation and artefacts. In this paper, we propose a novel framework, HiSplat, which introduces a hierarchical manner in generalizable 3D Gaussian Splatting to construct hierarchical 3D Gaussians via a coarse-to-fine strategy. Specifically, HiSplat generates large coarse-grained Gaussians to capture large-scale structures, followed by fine-grained Gaussians to enhance delicate texture details. To promote inter-scale interactions, we propose an Error Aware Module for Gaussian compensation and a Modulating Fusion Module for Gaussian repair. Our method achieves joint optimization of hierarchical representations, allowing for novel view synthesis using only two-view reference images. Comprehensive experiments on various datasets demonstrate that HiSplat significantly enhances reconstruction quality and cross-dataset generalization compared to prior single-scale methods. The corresponding ablation study and analysis of different-scale 3D Gaussians reveal the mechanism behind the effectiveness. Project website: https://open3dvlab.github.io/HiSplat/

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A feed-forward Gaussian-splatting model that subdivides each primary Gaussian into learned sub-pixel primitives, achieving state-of-the-art high-resolution novel-view synthesis from low-resolution inputs.

  2. MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Semantically enriched MASt3R correspondences plus a multi-attribute 3D consistency loss raise sparse-view ScanNet++ PSNR by >4.5 dB over Splatt3R and preserve quality under wide baselines.

  3. SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    SwiftGS uses episodic meta-training to predict geometry-radiation-decoupled Gaussian primitives and a lightweight SDF for zero-shot 3D satellite surface reconstruction with physics-aware rendering.

  4. LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images

    cs.CV 2025-07 reject novelty 6.0 of 10

    A feed-forward 3D Gaussian Splatting pipeline that incrementally fuses and compresses historical Gaussians using a 2D image-like representation.

  5. TRAN-D: 2D Gaussian Splatting-based Sparse-view Transparent Object Depth Reconstruction via Physics Simulation for Scene Update

    cs.RO 2025-07 conditional novelty 6.0 of 10

    TRAN-D reconstructs transparent-object depth from sparse views via segmentation-conditioned 2D Gaussian Splatting with an object-aware loss, and updates scenes after object removal using one image and physics simulation.

  6. JointSplat: Probabilistic Joint Flow-Depth Optimization for Sparse-View Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A feed-forward 3D Gaussian splatting method fuses depth and optical flow via a learned reliability mask, improving novel-view PSNR on RealEstate10K by 0.19 dB over its backbone.

  7. X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography

    eess.IV 2025-05 conditional novelty 6.0 of 10

    A large transformer with fixed-voxel Gaussian splatting reconstructs CT volumes from 6-10 X-ray projections in under a second, substantially beating prior sparse-view methods in simulation.

  8. MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A feed-forward architecture that reuses a frozen depth foundation model to predict 3D Gaussian primitives, improving novel view synthesis and cross-dataset generalization.

  9. Sparse-View 3D Reconstruction: Recent Advances and Open Challenges

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A comprehensive survey that organizes sparse-view 3D reconstruction methods into geometry-based, NeRF, 3DGS, and diffusion-based categories, with benchmarks and open challenges.

Pith tools