Related papers: $\pi^3$: Permutation-Equivariant Visual Geometry L…

Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a…

Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging because previous methods need to reconstruct the whole scene and…

Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually plausible reconstructions often contain errors, particularly…

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a…

While recent feed-forward 3D reconstruction models accelerate 3D reconstruction by jointly inferring dense geometry and camera poses in a single pass, their reliance on dense attention imposes a quadratic complexity, creating a prohibitive…

Image stitching aim to align two images taken from different viewpoints into one seamless, wider image. However, when the 3D scene contains depth variations and the camera baseline is significant, noticeable parallax occurs-meaning the…

We propose LookinGood^{\pi}, a novel neural re-rendering approach that is aimed to (1) improve the rendering quality of the low-quality reconstructed results from human performance capture system in real-time; (2) improve the generalization…

Recent advances in dense 3D reconstruction have led to significant progress, yet achieving accurate unified geometric prediction remains a major challenge. Most existing methods are limited to predicting a single geometry quantity from…

With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However, the excessive reliance on multi-view geometric annotations,…

Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide…

Handling geometric transformations, particularly rotations, remains a challenge in deep learning for computer vision. Standard neural networks lack inherent rotation invariance and typically rely on data augmentation or architectural…

We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses…

Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view images, e.g., from a fisheye camera, their performance…

In recent years, 3D visual foundation models pioneered by pointmap-based approaches such as DUSt3R have attracted a lot of interest, achieving impressive accuracy and strong generalization across diverse scenes. However, these methods are…

Visual re-localization means using a single image as input to estimate the camera's location and orientation relative to a pre-recorded environment. The highest-scoring methods are "structure based," and need the query camera's intrinsics…

We present 3DP3, a framework for inverse graphics that uses inference in a structured generative model of objects, scenes, and images. 3DP3 uses (i) voxel models to represent the 3D shape of objects, (ii) hierarchical scene graphs to…

Geometric foundation models hold promise for unconstrained dense geometry prediction from uncalibrated images. However, in current feed-forward designs, their predicted confidence scores are heuristic, lack probabilistic interpretation, and…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate camera poses as input, which could be difficult to obtain in…

Reconstructing dynamic 3D scenes (i.e., 4D geometry) from monocular video is an important yet challenging problem. Conventional multiview geometry-based approaches often struggle with dynamic motion, whereas recent learning-based methods…