Related papers: CanoVerse: 3D Object Scalable Canonicalization and…

We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without using any ground-truth 3D annotation. We accomplish this by…

Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurrently, large-scale vision language models show remarkable zero-shot capabilities. In this…

Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in…

Reconstructing 3D shape and pose of static objects from a single image is an essential task for various industries, including robotics, augmented reality, and digital content creation. This can be done by directly predicting 3D shape in…

We present a framework for learning 3D object shapes and dense cross-object 3D correspondences from just an unaligned category-specific image collection. The 3D shapes are generated implicitly as deformations to a category-specific signed…

While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform a systematic evaluation of the existing methods and find…

For years, researchers have been devoted to generalizable object perception and manipulation, where cross-category generalizability is highly desired yet underexplored. In this work, we propose to learn such cross-category skills via…

Recent progress in diffusion models significantly advances various image generation tasks. However, the current mainstream approach remains focused on building task-specific models, which have limited efficiency when supporting a wide range…

Reconstructing the underlying 3D surface of an object from a single image is a challenging problem that has received extensive attention from the computer vision community. Many learning-based approaches tackle this problem by learning a 3D…

Object pose estimation plays a vital role in embodied AI and computer vision, enabling intelligent agents to comprehend and interact with their surroundings. Despite the practicality of category-level pose estimation, current approaches…

Despite the remarkable progress of 3D generation, achieving controllability, i.e., ensuring consistency between generated 3D content and input conditions like edge and depth, remains a significant challenge. Existing methods often struggle…

Monocular 3D object detection (Mono3D) has achieved tremendous improvements with emerging large-scale autonomous driving datasets and the rapid development of deep learning techniques. However, caused by severe domain gaps (e.g., the field…

Generating realistic images of complex visual scenes becomes challenging when one wishes to control the structure of the generated images. Previous approaches showed that scenes with few entities can be controlled using scene graphs, but…

Salient object detection exemplifies data-bounded tasks where expensive pixel-precise annotations force separate model training for related subtasks like DIS and HR-SOD. We present a method that dramatically improves generalization through…

Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit…

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation,…

The field of video generation has expanded significantly in recent years, with controllable and compositional video generation garnering considerable interest. Most methods rely on leveraging annotations such as text, objects' bounding…

Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories, using only a few annotated support examples for guidance. Recent approaches either treat keypoints as isolated entities or rely…

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…

The choice of data representation is a key factor in the success of deep learning in geometric tasks. For instance, DUSt3R recently introduced the concept of viewpoint-invariant point maps, generalizing depth prediction and showing that all…