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

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…

Learning robust and effective representations of visual data is a fundamental task in computer vision. Traditionally, this is achieved by training models with labeled data which can be expensive to obtain. Self-supervised learning attempts…

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness,…

With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as…

Recent advances in deep learning have led to a data-centric intelligence i.e. artificially intelligent models unlocking the potential to ingest a large amount of data and be really good at performing digital tasks such as text-to-image…

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…

Researchers have now achieved great success on dealing with 2D images using deep learning. In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention. Many advanced techniques for 3D shapes have been…

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply…

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…

Learning from 3D protein structures has gained wide interest in protein modeling and structural bioinformatics. Unfortunately, the number of available structures is orders of magnitude lower than the training data sizes commonly used in…

Representing scenes at the granularity of objects is a prerequisite for scene understanding and decision making. We propose PriSMONet, a novel approach based on Prior Shape knowledge for learning Multi-Object 3D scene decomposition and…

How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set…

Most 3D neural networks are trained from scratch owing to the lack of large-scale labeled 3D datasets. In this paper, we present a novel 3D pretraining method by leveraging 2D networks learned from rich 2D datasets. We propose the…

Protein representation learning aims to learn informative protein embeddings capable of addressing crucial biological questions, such as protein function prediction. Although sequence-based transformer models have shown promising results by…

Holistic 3D scene understanding entails estimation of both layout configuration and object geometry in a 3D environment. Recent works have shown advances in 3D scene estimation from various input modalities (e.g., images, 3D scans), by…

Recent learning approaches that implicitly represent surface geometry using coordinate-based neural representations have shown impressive results in the problem of multi-view 3D reconstruction. The effectiveness of these techniques is,…

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the…

Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein function or structure. Existing approaches usually pretrain protein language models on a large number of unlabeled amino acid…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…