Related papers: Share With Thy Neighbors: Single-View Reconstructi…

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2)…

Single-view 3D reconstruction is currently approached from two dominant perspectives: reconstruction of scenes with limited diversity using 3D data supervision or reconstruction of diverse singular objects using large image priors. However,…

We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in…

Reconstructing 3D objects from a single image guided by pretrained diffusion models has demonstrated promising outcomes. However, due to utilizing the case-agnostic rigid strategy, their generalization ability to arbitrary cases and the 3D…

Semantic reconstruction of indoor scenes refers to both scene understanding and object reconstruction. Existing works either address one part of this problem or focus on independent objects. In this paper, we bridge the gap between…

We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary view. We do so by reformulating view…

This paper presents a self-supervised method for learning reliable visual correspondence from unlabeled videos. We formulate the correspondence as finding paths in a joint space-time graph, where nodes are grid patches sampled from frames,…

In this paper, we present a new perspective towards image-based shape generation. Most existing deep learning based shape reconstruction methods employ a single-view deterministic model which is sometimes insufficient to determine a single…

We propose a modular framework for single-view indoor scene 3D reconstruction, where several core modules are powered by diffusion techniques. Traditional approaches for this task often struggle with the complex instance shapes and…

Augmentation-based self-supervised learning methods have shown remarkable success in self-supervised visual representation learning, excelling in learning invariant features but often neglecting equivariant ones. This limitation reduces the…

Unsupervised image retrieval aims to learn an efficient retrieval system without expensive data annotations, but most existing methods rely heavily on handcrafted feature descriptors or pre-trained feature extractors. To minimize human…

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic…

Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning. Most approaches regress the full object shape in a canonical pose, possibly…

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for…

Prior research on self-supervised learning has led to considerable progress on image classification, but often with degraded transfer performance on object detection. The objective of this paper is to advance self-supervised pretrained…

We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent advances in neural rendering and probabilistic image generation. Existing approaches typically build on neural rendering with re-projected features but…

Learning the prior knowledge of the 3D human-object spatial relation is crucial for reconstructing human-object interaction from images and understanding how humans interact with objects in 3D space. Previous works learn this prior from…

Our goal in this paper is to discover near duplicate patterns in large collections of artworks. This is harder than standard instance mining due to differences in the artistic media (oil, pastel, drawing, etc), and imperfections inherent in…

Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes…

In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is…