paper-with-me

Papers

ZipSplat: Fewer Gaussians, Better Splats

2026-06-03 · Alexander Veicht, Sunghwan Hong, Dániel Baráth, Marc Pollefeys arxiv

Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel, tying the representation budget to camera resolution rather than scene complexity. A flat wall and a richly textured object thus produce equally many Gaussians despite very different geometric needs. We propose ZipSplat, a token-based feed-forward model that decouples Gaussian placement from the pixel grid. A multi-view backbone extracts dense visual tokens, and k-means clustering compresses them into a compact set of scene tokens. Cross- and self-attention refine these tokens, and a lightweight MLP decodes each into a group of Gaussians with unconstrained 3D positions. Because clustering is applied at inference, a single trained model spans the quality-efficiency curve without retraining. ZipSplat operates without ground-truth poses or intrinsics, yet sets a new state of the art on DL3DV and RealEstate10K with ${\sim}6{\times}$ fewer Gaussians than pixel-aligned methods, surpassing the best pose-free baseline by 2.1dB and 1.2dB PSNR, respectively. It further generalizes zero-shot to Mip-NeRF360 and ScanNet++, outperforming all comparable baselines. Our project page is at https://veichta.com/zipsplat.

📄 PDF Abstract BibTeX arXiv:2606.05102

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency

2024-10-10 · Florian Hahlbohm, Fabian Friederichs, Tim Weyrich, Linus Franke 외

3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is cr…

3DGSInverse Rendering

DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models

2024-12-11 · Kevin Miao, Harsh Agrawal, Qihang Zhang, Federico Semeraro 외

Generating high-quality 3D content requires models capable of learning robust distributions of complex scenes and the real-world objects within them. Recent Gaussian-based 3D reconstruction techniques have achieved impre…

3D Generation3D ReconstructionDenoisingImage to 3D+2

HUGS: Human Gaussian Splats

2023-11-29 · CVPR 2024 1 · Muhammed Kocabas, Jen-Hao Rick Chang, James Gabriel, Oncel Tuzel 외

Recent advances in neural rendering have improved both training and rendering times by orders of magnitude. While these methods demonstrate state-of-the-art quality and speed, they are designed for photogrammetry of stat…

3DGSNeural RenderingNovel View Synthesis

G3Splat: Geometrically Consistent Generalizable Gaussian Splatting

2025-12-19 · Mehdi Hosseinzadeh, Shin-Fang Chng, Yi Xu, Simon Lucey 외 arxiv

3D Gaussians have become a powerful scene representation for real-time splatting and high-quality novel-view synthesis. This has motivated generalizable splatting -- methods that adapt feed-forward geometry prediction ne…

Pose Estimation

GeoTexDensifier: Geometry-Texture-Aware Densification for High-Quality Photorealistic 3D Gaussian Splatting

2024-12-22 · Hanqing Jiang, Xiaojun Xiang, Han Sun, Hongjie Li 외

3D Gaussian Splatting (3DGS) has recently attracted wide attentions in various areas such as 3D navigation, Virtual Reality (VR) and 3D simulation, due to its photorealistic and efficient rendering performance. High-qual…

3DGSNovel View Synthesis