Related papers: AnyOKP: One-Shot and Instance-Aware Object Keypoin…
In deformable object manipulation, we often want to interact with specific segments of an object that are only defined in non-deformed models of the object. We thus require a system that can recognize and locate these segments in sensor…
This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations in a harmonious way. Instead of tuning parameters for each object, our model is trained only…
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…
Articulated object manipulation is a critical capability for robots to perform various tasks in real-world scenarios. Composed of multiple parts connected by joints, articulated objects are endowed with diverse functional mechanisms through…
Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the traditional representation learning that is based…
Efficient and reliable methods for training of object detectors are in higher demand than ever, and more and more data relevant to the field is becoming available. However, large datasets like Open Images Dataset v4 (OID) are sparsely…
Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene…
We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence. Our training framework uses true correspondences, obtained by matching annotated image…
By estimating 3D shape and instances from a single view, we can capture information about an environment quickly, without the need for comprehensive scanning and multi-view fusion. Solving this task for composite scenes (such as object…
Video object segmentation aims at accurately segmenting the target object regions across consecutive frames. It is technically challenging for coping with complicated factors (e.g., shape deformations, occlusion and out of the lens). Recent…
Most of existing blind omnidirectional image quality assessment (BOIQA) models rely on viewport generation by modeling user viewing behavior or transforming omnidirectional images (OIs) into varying formats; however, these methods are…
Reliable localization is critical for robot navigation, yet most existing systems implicitly assume that all viewing directions at a location are equally informative. In practice, localization becomes unreliable when the robot observes…
Multiple object tracking (MOT) is a crucial task in computer vision society. However, most tracking-by-detection MOT methods, with available detected bounding boxes, cannot effectively handle static, slow-moving and fast-moving camera…
Objects in videos are typically characterized by continuous smooth motion. We exploit continuous smooth motion in three ways. 1) Improved accuracy by using object motion as an additional source of supervision, which we obtain by…
Monocular 3D detection has drawn much attention from the community due to its low cost and setup simplicity. It takes an RGB image as input and predicts 3D boxes in the 3D space. The most challenging sub-task lies in the instance depth…
Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring transferable visual representations. To leverage the valuable knowledge encoded within these models for…
Creating computer vision datasets requires careful planning and lots of time and effort. In robotics research, we often have to use standardized objects, such as the YCB object set, for tasks such as object tracking, pose estimation,…
Unpaired Image-to-image Translation is a new rising and challenging vision problem that aims to learn a mapping between unaligned image pairs in diverse domains. Recent advances in this field like MUNIT and DRIT mainly focus on…
Object-oriented embodied navigation aims to locate specific objects, defined by category or depicted in images. Existing methods often struggle to generalize to open vocabulary goals without extensive training data. While recent advances in…
Vision-language models enable open-world classification of objects without the need for any retraining. While this zero-shot paradigm marks a significant advance, even today's best models exhibit skewed performance when objects are…