Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of
complex videos from a text description. However, most existing models lack fine-grained …

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 …

Advancements in 3D scene reconstruction have transformed 2D images from the real world
into 3D models, producing realistic 3D results from hundreds of input photos. Despite great …

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 …

Monocular metric depth estimation (MMDE) is a crucial task to solve for indoor scene
reconstruction on edge devices. Despite this importance, existing models are sensitive to …

3D Semantic Occupancy Prediction is fundamental for spatial understanding as it provides a
comprehensive semantic cognition of surrounding environments. However, prevalent …

Synthesizing a novel view from a single input image is a challenging task. Traditionally, this
task was approached by estimating scene depth, warping, and inpainting, with machine …

Numerous works have recently integrated 3D camera control into foundational text-to-video
models, but the resulting camera control is often imprecise, and video generation quality …

Generalized feed-forward Gaussian models have achieved significant progress in sparse-
view 3D reconstruction by leveraging prior knowledge from large multi-view datasets …

We introduce a diffusion model for Gaussian Splats, SplatDiffusion, to enable generation of
three-dimensional structures from single images, addressing the ill-posed nature of lifting 2D …