Pith. sign in

REVIEW 6 cited by

GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors

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 2406.10111 v1 pith:G7NIZMNN submitted 2024-06-14 cs.CV

GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors

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

Achieving high-resolution novel view synthesis (HRNVS) from low-resolution input views is a challenging task due to the lack of high-resolution data. Previous methods optimize high-resolution Neural Radiance Field (NeRF) from low-resolution input views but suffer from slow rendering speed. In this work, we base our method on 3D Gaussian Splatting (3DGS) due to its capability of producing high-quality images at a faster rendering speed. To alleviate the shortage of data for higher-resolution synthesis, we propose to leverage off-the-shelf 2D diffusion priors by distilling the 2D knowledge into 3D with Score Distillation Sampling (SDS). Nevertheless, applying SDS directly to Gaussian-based 3D super-resolution leads to undesirable and redundant 3D Gaussian primitives, due to the randomness brought by generative priors. To mitigate this issue, we introduce two simple yet effective techniques to reduce stochastic disturbances introduced by SDS. Specifically, we 1) shrink the range of diffusion timestep in SDS with an annealing strategy; 2) randomly discard redundant Gaussian primitives during densification. Extensive experiments have demonstrated that our proposed GaussainSR can attain high-quality results for HRNVS with only low-resolution inputs on both synthetic and real-world datasets. Project page: https://chchnii.github.io/GaussianSR/

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

    cs.CV 2026-07 conditional novelty 6.0

    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. AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting

    cs.CV 2026-07 unverdicted novelty 6.0

    AnchorSplat introduces a source-free 3D refinement network using Point Anchor Mechanism for consistent detail synthesis in Gaussian Splatting and releases the 3DGS-SR benchmark, reporting SOTA speed and zero-shot performance.

  3. AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting

    cs.CV 2026-07 conditional novelty 6.0

    A single-pass 3D-native network upgrades low-quality Gaussian Splatting assets with local geometric anchors, delivering SOTA fidelity on a new benchmark at up to 10^5× the speed of optimization pipelines.

  4. HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video

    cs.CV 2026-06 unverdicted novelty 6.0

    HiReFF presents a feed-forward framework for 2K human video reconstruction from uncalibrated sparse-view videos via scale-synchronized calibration, Gaussian masking, and high-resolution side-tuning.

  5. ConFi-GS Confidence-Guided High-Frequency Injection for 3D Gaussian Splatting Super-Resolution

    cs.CV 2026-05 unverdicted novelty 5.0

    Proposes a reliability-aware frequency modeling framework using geometry-guided detail-demand prior and frequency-aware reliability map to guide high-frequency detail injection in low-resolution 3DGS, with a unified o...

  6. GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance

    cs.CV 2026-05 unverdicted novelty 5.0

    GaussianZoom enables high-fidelity extreme zoom-in 3D rendering from low-res inputs via an iterative framework combining geometry-consistent modeling, depth-based super-resolution, VLM detail synthesis, and an expanda...