REVIEW 7 cited by
Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
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
abstract
Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (\textit{e.g.}, $\times$ 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast arbitrary-scale super-resolution. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical ana
Forward citations
Cited by 7 Pith papers
-
PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution
A 2D Gaussian Splatting framework with MRI-specific anatomical priors, physics-constrained intensity modeling, and meta-learning domain adaptation achieves state-of-the-art MRI super-resolution while showing that inte...
-
GarmentZoom: Generating Zoomable Images from Garment Listings
GarmentZoom trains one model to synthesize unaligned close-up details into full-view garment images across continuous scales 3-20x without per-instance tuning.
-
Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection
FocusMamba uses event-camera activity to adaptively prune uninformative tokens in both RGB and event streams, improving detection accuracy and cutting FLOPs.
-
2D Gaussian Splatting with Semantic Alignment for Image Inpainting
A 2D Gaussian Splatting encoder-rasterization network with DINO-based semantic alignment achieves competitive image inpainting results.
-
UltraZoom: Generating Gigapixel Images from Regular Photos
UltraZoom generates coherent gigapixel imagery from a regular full view and sparse close-ups by per-instance fine-tuning of a pretrained generative model with video-based registration.
-
MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scale
A cascaded, segmentation-conditioned, per-instance diffusion method synthesizes globally coherent gigapixel microscopic detail from a phone photo and sparse microscope references at up to 350×.
-
Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment
FG-PAN improves zero-shot brain tumor subtype classification by aligning refined visual patch features with LLM-generated fine-grained text prototypes.
Discussion (0). Continue with ORCID to comment.