The field of visual computing is rapidly advancing due to the emergence of generative
artificial intelligence (AI), which unlocks unprecedented capabilities for the generation …

Efficient rendering of photo‐realistic virtual worlds is a long standing effort of computer
graphics. Modern graphics techniques have succeeded in synthesizing photo‐realistic …

Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera
intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain yet …

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 …

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 …

Abstract 3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at
rendering photorealistic novel views of complex scenes. However recovering a high-quality …

Recent advances in real-time neural rendering using point-based techniques have enabled
broader adoption of 3D representations. However, foundational approaches like 3D …

Neural radiance fields enable state-of-the-art photorealistic view synthesis. However,
existing radiance field representations are either too compute-intensive for real-time …

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 …

We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried
point on any physical surface throughout a video sequence. Our approach employs two …