Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

SLAM is an abbreviation for simultaneous localization and map**, which is a technique for
estimating sensor motion and reconstructing structure in an unknown environment …

Large multimodal models (LMMs) extend large language models (LLMs) with multi-sensory
skills, such as visual understanding, to achieve stronger generic intelligence. In this paper …

Finding correspondences between images is a fundamental problem in computer vision. In
this paper, we show that correspondence emerges in image diffusion models without any …

We introduce CoTracker, a transformer-based model that tracks a large number of 2D points
in long video sequences. Differently from most existing approaches that track points …

We present a diffusion-based model for 3D-aware generative novel view synthesis from as
few as a single input image. Our model samples from the distribution of possible renderings …

Existing NeRF-based methods for large scene reconstruction often have limitations in visual
quality and rendering speed. While the recent 3D Gaussian Splatting works well on small …

We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D
meshes generation from a single unposed image in the wild using both2D and 3D priors. In …

We present a new test-time optimization method for estimating dense and long-range motion
from a video sequence. Prior optical flow or particle video tracking algorithms typically …

We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D
Gaussian primitives from 2–4 posed sparse images in∼ 0.23 s on single A100 GPU. Our …