Pith. sign in

REVIEW 7 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

classification cs.CV
keywords gaussiandiffusionhigh-resolutionlow-resolutionpriorsdatagaussiansrhigh-quality
verification ladder T0 review T1 audit T2 compute T3 formal
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 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. CLEAR: Conflict-aware Learning via Evidence-guided Adaptive Routing for Unified Sparse-View 3D Gaussian Super-Resolution

    cs.CV 2026-08 conditional novelty 6.0 of 10

    CLEAR performs single-stage joint training of a 3D Gaussian scene under low- and high-resolution supervision, using conflict-aware gradient correction and evidence-guided detail routing to reach state-of-the-art spars...

  2. 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.

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

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    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. SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting

    cs.CV 2025-12 conditional novelty 6.0 of 10

    SplatSuRe selectively applies single-image super-resolution only to 3D regions undersampled by low-resolution training views, yielding sharper and more consistent 3D Gaussian Splatting renders.

  5. R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision

    cs.CV 2025-06 conditional novelty 6.0 of 10

    The survey formalizes degradation-aware rendering for 3D Low-Level Vision and organizes roughly 100 methods on super-resolution, deblurring, weather removal, restoration, and enhancement in NeRF and 3DGS pipelines.

  6. PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PBR-SR super-resolves PBR texture maps (albedo, roughness, metallic, normal) in a zero-shot way by optimizing textures so differentiable renderings match super-resolved multi-view renderings from a pretrained image SR model.

  7. SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training

    cs.CV 2025-12 conditional novelty 5.0 of 10

    A test-time-trained feedforward model that propagates 2D edits onto 3D Gaussian attributes at interactive speeds.

Pith tools