REVIEW 7 cited by
SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing
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
read the original abstract
In this paper, we present a Scale-adaptive method for Anti-aliasing Gaussian Splatting (SA-GS). While the state-of-the-art method Mip-Splatting needs modifying the training procedure of Gaussian splatting, our method functions at test-time and is training-free. Specifically, SA-GS can be applied to any pretrained Gaussian splatting field as a plugin to significantly improve the field's anti-alising performance. The core technique is to apply 2D scale-adaptive filters to each Gaussian during test time. As pointed out by Mip-Splatting, observing Gaussians at different frequencies leads to mismatches between the Gaussian scales during training and testing. Mip-Splatting resolves this issue using 3D smoothing and 2D Mip filters, which are unfortunately not aware of testing frequency. In this work, we show that a 2D scale-adaptive filter that is informed of testing frequency can effectively match the Gaussian scale, thus making the Gaussian primitive distribution remain consistent across different testing frequencies. When scale inconsistency is eliminated, sampling rates smaller than the scene frequency result in conventional jaggedness, and we propose to integrate the projected 2D Gaussian within each pixel during testing. This integration is actually a limiting case of super-sampling, which significantly improves anti-aliasing performance over vanilla Gaussian Splatting. Through extensive experiments using various settings and both bounded and unbounded scenes, we show SA-GS performs comparably with or better than Mip-Splatting. Note that super-sampling and integration are only effective when our scale-adaptive filtering is activated. Our codes, data and models are available at https://github.com/zsy1987/SA-GS.
Forward citations
Cited by 7 Pith papers
-
Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding
Representing bounding-box coordinates as axis-specific hundreds, tens, and ones tokens, plus a geometry-aware GRPO reward, improves generative visual grounding accuracy.
-
IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models
Training a coordinate-generating VLM with an IoU-aware distillation loss from a teacher that sees the ground-truth box marked on the image improves referring-expression grounding by ~3-4 accuracy points.
-
NeRF Is a Valuable Assistant for 3D Gaussian Splatting
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.
-
SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting
SurfaceSplat combines SDF-based coarse meshes with Gaussian splatting to improve sparse-view reconstruction and rendering, but the ablations do not isolate the effect of each component.
-
LOD-GS: Level-of-Detail-Sensitive 3D Gaussian Splatting for Detail Conserved Anti-Aliasing
A learning-based, sampling-rate-dependent filter for 3D Gaussian Splatting improves anti-aliased rendering across resolutions and camera distances.
-
Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
MixGS trains a holistic 3D Gaussian Splatting model with a view-aware decoder and a mixing operation, reporting state-of-the-art rendering quality on four large-scale scenes.
-
Challenger: Affordable Adversarial Driving Video Generation
A framework for automatic generation of photorealistic adversarial driving videos, shown to sharply increase collision rates of end-to-end autonomous driving models.
Discussion (0). Sign in to comment.