Skip to yearly menu bar Skip to main content


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

David Charatan · Sizhe Lester Li · Andrea Tagliasacchi · Vincent Sitzmann

Arch 4A-E Poster #138
[ ]
Fri 21 Jun 10:30 a.m. PDT — noon PDT
Oral presentation: Orals 5B 3D from multiview and sensors
Fri 21 Jun 9 a.m. PDT — 10:30 a.m. PDT


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. Additional materials can be found on the anonymous project website (

Live content is unavailable. Log in and register to view live content