Related papers: Learning Viewpoint-Agnostic Visual Representations…
To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…
Computer graphics, 3D computer vision and robotics communities have produced multiple approaches to represent and generate 3D shapes, as well as a vast number of use cases. However, single-view reconstruction remains a challenging topic…
Inspired by the great success achieved by CNN in image recognition, view-based methods applied CNNs to model the projected views for 3D object understanding and achieved excellent performance. Nevertheless, multi-view CNN models cannot…
We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…
In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the…
Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…
Thanks to its precise spatial referencing, 3D point cloud visual grounding is essential for deep understanding and dynamic interaction in 3D environments, encompassing 3D Referring Expression Comprehension (3DREC) and Segmentation (3DRES).…
Both humans and deep learning models can recognize objects from 3D shapes depicted with sparse visual information, such as a set of points randomly sampled from the surfaces of 3D objects (termed a point cloud). Although deep learning…
Although neural radiance fields (NeRF) have shown impressive advances for novel view synthesis, most methods typically require multiple input images of the same scene with accurate camera poses. In this work, we seek to substantially reduce…
3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect),…
We propose a novel approach to performing fine-grained 3D manipulation of image content via a convolutional neural network, which we call the Transformable Bottleneck Network (TBN). It applies given spatial transformations directly to a…
We propose a novel deep reinforcement learning-based approach for 3D object reconstruction from monocular images. Prior works that use mesh representations are template based. Thus, they are limited to the reconstruction of objects that…
Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in…
This paper addresses the challenges in representation learning of 3D shape features by investigating state-of-the-art backbones paired with both contrastive supervised and self-supervised learning objectives. Computer vision methods…
We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our…
In this paper, we propose a set of transform-based neural network layers as an alternative to the $3\times3$ Conv2D layers in Convolutional Neural Networks (CNNs). The proposed layers can be implemented based on orthogonal transforms such…
Multi-view projection techniques have shown themselves to be highly effective in achieving top-performing results in the recognition of 3D shapes. These methods involve learning how to combine information from multiple view-points. However,…
Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not…
Humans have a strong intuitive understanding of the 3D environment around us. The mental model of the physics in our brain applies to objects of different materials and enables us to perform a wide range of manipulation tasks that are far…