paper-with-me

홈 › Papers

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

2023-12-19 · CVPR 2024 1 · David Charatan, Sizhe Li, Andrea Tagliasacchi, Vincent Sitzmann

We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradients through the Gaussian splatting representation. We benchmark our method on wide-baseline novel view synthesis on the real-world RealEstate10k and ACID datasets, where we outperform state-of-the-art light field transformers and accelerate rendering by 2.5 orders of magnitude while reconstructing an interpretable and editable 3D radiance field.

📄 PDF Abstract BibTeX arXiv:2312.12337

Code (1)

dcharatan/pixelsplat 공식 구현 jax

Tasks

3D ReconstructionGeneralizable Novel View SynthesisNovel View Synthesis

Similar Papers 제목 키워드 기반

Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

2024-08-25 · Brandon Smart, Chuanxia Zheng, Iro Laina, Victor Adrian Prisacariu

In this paper, we introduce Splatt3R, a pose-free, feed-forward method for in-the-wild 3D reconstruction and novel view synthesis from stereo pairs. Given uncalibrated natural images, Splatt3R can predict 3D Gaussian Spl…

3D geometry3D ReconstructionNovel View Synthesis

SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting

2024-09-16 · Mohammad Nomaan Qureshi, Sparsh Garg, Francisco Yandun, David Held 외

Sim2Real transfer, particularly for manipulation policies relying on RGB images, remains a critical challenge in robotics due to the significant domain shift between synthetic and real-world visual data. In this paper, w…

MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Rendering

2024-10-11 · Jaehoon Choi, Yonghan Lee, Hyungtae Lee, Heesung Kwon 외

Recently, 3D Gaussian splatting has gained attention for its capability to generate high-fidelity rendering results. At the same time, most applications such as games, animation, and AR/VR use mesh-based representations …

NeRFNeural Rendering

P-GSVC: Layered Progressive 2D Gaussian Splatting for Scalable Image and Video

2026-03-11 · Longan Wang, Yuang Shi, Wei Tsang Ooi arxiv

Gaussian splatting has emerged as a competitive explicit representation for image and video reconstruction. In this work, we present P-GSVC, the first layered progressive 2D Gaussian splatting framework that provides a u…

Video Reconstruction

SA-GS: Semantic-Aware Gaussian Splatting for Large Scene Reconstruction with Geometry Constrain

2024-05-27 · Butian Xiong, Xiaoyu Ye, Tze Ho Elden Tse, Kai Han 외

With the emergence of Gaussian Splats, recent efforts have focused on large-scale scene geometric reconstruction. However, most of these efforts either concentrate on memory reduction or spatial space division, neglectin…

3D geometry