Pith. sign in

REVIEW 7 cited by

GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting

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 2402.10259 v4 pith:SQOOPGDO submitted 2024-02-15 cs.CV cs.GR

Chen Yang , Sikuang Li , Jiemin Fang , Ruofan Liang , Lingxi Xie , Xiaopeng Zhang , Wei Shen , Qi Tian This is my paper · ORCID
classification cs.CVcs.GR
keywords gaussianobjectgaussianimagesobjectviewsinformationonlyachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However, images from sparse views only contain very limited 3D information, leading to two significant challenges: 1) Difficulty in building multi-view consistency as images for matching are too few; 2) Partially omitted or highly compressed object information as view coverage is insufficient. To tackle these challenges, we propose GaussianObject, a framework to represent and render the 3D object with Gaussian splatting that achieves high rendering quality with only 4 input images. We first introduce techniques of visual hull and floater elimination, which explicitly inject structure priors into the initial optimization process to help build multi-view consistency, yielding a coarse 3D Gaussian representation. Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined. We design a self-generating strategy to obtain image pairs for training the repair model. We further design a COLMAP-free variant, where pre-given accurate camera poses are not required, which achieves competitive quality and facilitates wider applications. GaussianObject is evaluated on several challenging datasets, including MipNeRF360, OmniObject3D, OpenIllumination, and our-collected unposed images, achieving superior performance from only four views and significantly outperforming previous SOTA methods. Our demo is available at https://gaussianobject.github.io/, and the code has been released at https://github.com/GaussianObject/GaussianObject.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. 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.

  2. NeRF Is a Valuable Assistant for 3D Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    NeRF-GS jointly optimizes a NeRF and a 3D Gaussian Splatting model in one scene, using shared features, residual corrections, and mutual loss constraints to beat both standalone methods.

  3. Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Zero-P-to-3 fuses multi-view diffusion, a restoration prior, and a coarse 3D Gaussian rendering in DDIM sampling, then refines with rotated views, and reports improved invisible-region reconstruction from partial-view...

  4. Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

    cs.GR 2025-08 conditional novelty 5.0 of 10

    A feed-forward pipeline predicts 3D human Gaussian splats from two input images (front and back) in 190 ms, using a DUSt3R-style point cloud predictor with extra side-view heads, nearest-neighbor color warping, and a ...

  5. Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A split-then-clone densification schedule with energy-guided multi-resolution training roughly halves 3D Gaussian Splatting training time while keeping reconstruction quality.

  6. Improving Novel view synthesis of 360$^\circ$ Scenes in Extremely Sparse Views by Jointly Training Hemisphere Sampled Synthetic Images

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A pipeline that samples and enhances synthetic upper-hemisphere views from a DUSt3R point cloud to train 3D Gaussian Splatting, improving four-view 360-degree novel view synthesis.

  7. 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