Related papers: Pri3D: Can 3D Priors Help 2D Representation Learni…

Single-image 3D reconstruction is a research challenge focused on predicting 3D object shapes from single-view images. This task requires significant data acquisition to predict both visible and occluded portions of the shape. Furthermore,…

3D pose estimation from a single image is a challenging task in computer vision. We present a weakly supervised approach to estimate 3D pose points, given only 2D pose landmarks. Our method does not require correspondences between 2D and 3D…

Multimodal imaging and correlative analysis typically require image alignment. Contrastive learning can generate representations of multimodal images, reducing the challenging task of multimodal image registration to a monomodal one.…

While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose…

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…

Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…

Spatial perception aims to estimate camera motion and scene structure from visual observations, a problem traditionally addressed through geometric modeling and physical consistency constraints. Recent learning-based methods have…

Modern deep learning developments create new opportunities for 3D mapping technology, scene reconstruction pipelines, and virtual reality development. Despite advances in 3D deep learning technology, direct training of deep learning models…

In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates…

Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area. However, its efficacy is largely constrained due to the…

3D reconstruction and novel view rendering can greatly benefit from geometric priors when the input views are not sufficient in terms of coverage and inter-view baselines. Deep learning of geometric priors from 2D images often requires each…

State-of-the-art learning-based monocular 3D reconstruction methods learn priors over object categories on the training set, and as a result struggle to achieve reasonable generalization to object categories unseen during training. In this…

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on…

Can the latent spaces of modern generative neural rendering models serve as representations for 3D-aware discriminative visual understanding tasks? We use retrieval as a proxy for measuring the metric learning properties of the latent…

Recent advances in deep learning have shown that learning robust feature representations is critical for the success of many computer vision tasks, including medical image segmentation. In particular, both transformer and…

Real-time efficient perception is critical for autonomous navigation and city scale sensing. Orthogonal to architectural improvements, streaming perception approaches have exploited adaptive sampling improving real-time detection…

Supervised deep convolutional neural networks (DCNNs) are currently one of the best computational models that can explain how the primate ventral visual stream solves object recognition. However, embodied cognition has not been considered…

Self-supervised learning has proved effective for skeleton-based human action understanding, which is an important yet challenging topic. Previous works mainly rely on contrastive learning or masked motion modeling paradigm to model the…

Neural implicit modeling permits to achieve impressive 3D reconstruction results on small objects, while it exhibits significant limitations in large indoor scenes. In this work, we propose a novel neural implicit modeling method that…

In this paper we present a novel unsupervised representation learning approach for 3D shapes, which is an important research challenge as it avoids the manual effort required for collecting supervised data. Our method trains an RNN-based…