REVIEW 7 cited by
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS
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
Recent advances in view synthesis and real-time rendering have achieved photorealistic quality at impressive rendering speeds. While Radiance Field-based methods achieve state-of-the-art quality in challenging scenarios such as in-the-wild captures and large-scale scenes, they often suffer from excessively high compute requirements linked to volumetric rendering. Gaussian Splatting-based methods, on the other hand, rely on rasterization and naturally achieve real-time rendering but suffer from brittle optimization heuristics that underperform on more challenging scenes. In this work, we present RadSplat, a lightweight method for robust real-time rendering of complex scenes. Our main contributions are threefold. First, we use radiance fields as a prior and supervision signal for optimizing point-based scene representations, leading to improved quality and more robust optimization. Next, we develop a novel pruning technique reducing the overall point count while maintaining high quality, leading to smaller and more compact scene representations with faster inference speeds. Finally, we propose a novel test-time filtering approach that further accelerates rendering and allows to scale to larger, house-sized scenes. We find that our method enables state-of-the-art synthesis of complex captures at 900+ FPS.
Forward citations
Cited by 7 Pith papers
-
ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction
ContraGS trains 3D Gaussian Splatting directly on codebook-compressed representations, cutting peak model memory ~3.5x with small quality loss.
-
Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians
Can3Tok tokenizes scene-level 3D Gaussian splats into canonical latent tokens with normalization and saliency filtering, enabling reconstruction and text/image-to-3D generation.
-
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.
-
SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting
SurfFill completes missing thin structures in LiDAR point clouds by focusing Gaussian surfel splatting on density-ambiguous regions surrounding the gaps.
-
Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
Jointly optimizing RGB and four additional spectral bands in one 3D Gaussian Splatting model, after an RGB-only warm-up and with spectrum-aware densification, outperforms per-band models and slightly improves RGB via ...
-
Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
Learned per-splat Beta-distributed confidence scores enable test-time pruning of 3D Gaussian splats with minor quality loss, and average confidence is proposed as a scene quality metric.
-
Efficient 3D Gaussian Splatting with Axis-Shared Rasterization and Order-independent Transmittance
A 3D Gaussian Splatting accelerator uses axis-shared rasterization and a trained MLP to replace sorting, reporting large speedups over edge GPUs with about 1 dB PSNR loss.
Discussion (0). Continue with ORCID to comment.