We introduce MVSplat, an efficient model that, given sparse multi-view images as input,
predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we …

In recent years, neural implicit surface reconstruction has emerged as a popular paradigm
for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural …

We introduce Free3D a simple accurate method for monocular open-set novel view
synthesis (NVS). Similar to Zero-1-to-3 we start from a pre-trained 2D image generator for …

Given a single image of a 3D object this paper proposes a novel method (named
ConsistNet) that can generate multiple images of the same object as if they are captured …

We present MVSGaussian, a new generalizable 3D Gaussian representation approach
derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes …

We introduce MVSplat360, a feed-forward approach for 360 {\deg} novel view synthesis
(NVS) of diverse real-world scenes, using only sparse observations. This setting is …

We introduce Deceptive-NeRF, a novel methodology for few-shot NeRF reconstruction,
which leverages diffusion models to synthesize plausible pseudo-observations to improve …

We propose NViST a transformer-based model for efficient and generalizable novel-view
synthesis from a single image for real-world scenes. In contrast to many methods that are …

Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices
involve constructing variance-based cost volumes for geometry reconstruction and encoding …

Abstract We present Multi-Baseline Radiance Fields (MuRF) a general feed-forward
approach to solving sparse view synthesis under multiple different baseline settings (small …