REVIEW 13 cited by
HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
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
Signed reviews
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/
Forward citations
Cited by 13 Pith papers
-
SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization
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.
-
MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction
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.
-
SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery
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.
-
LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images
A feed-forward 3D Gaussian Splatting pipeline that incrementally fuses and compresses historical Gaussians using a 2D image-like representation.
-
TRAN-D: 2D Gaussian Splatting-based Sparse-view Transparent Object Depth Reconstruction via Physics Simulation for Scene Update
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.
-
JointSplat: Probabilistic Joint Flow-Depth Optimization for Sparse-View Gaussian Splatting
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.
-
X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography
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.
-
MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models
A feed-forward architecture that reuses a frozen depth foundation model to predict 3D Gaussian primitives, improving novel view synthesis and cross-dataset generalization.
-
PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting
A feed-forward Gaussian splatting system that synthesizes novel 4K panoramic views from two wide-baseline inputs, using Fibonacci-lattice Gaussians and memory-efficient training.
-
Splatter-360: Generalizable 360$^{\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images
Splatter-360 is an end-to-end generalizable 3D Gaussian splatting model that builds a spherical cost volume to improve geometry and rendering from wide-baseline panoramic images.
-
InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding
InstanceSplat predicts 3D Gaussians with per-object identity and language-aligned semantics from unposed multi-view images in a single forward pass, enabling rendering, instance segmentation, and open-vocabulary queries.
-
PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation
A pipeline that infers object material with a multimodal model and optimizes material parameters with optical flow from video diffusion to simulate 4D dynamic scenes.
-
Sparse-View 3D Reconstruction: Recent Advances and Open Challenges
A comprehensive survey that organizes sparse-view 3D reconstruction methods into geometry-based, NeRF, 3DGS, and diffusion-based categories, with benchmarks and open challenges.
Discussion (0). Continue with ORCID to comment.