Related papers: SceneScore: Learning a Cost Function for Object Ar…

To understand a scene in depth not only involves locating/recognizing individual objects, but also requires to infer the relationships and interactions among them. However, since the distribution of real-world relationships is seriously…

Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, existing methods struggle in cluttered environments, often exhibiting prohibitive computational cost,…

We consider robotic pick-and-place of partially visible, novel objects, where goal placements are non-trivial, e.g., tightly packed into a bin. One approach is (a) use object instance segmentation and shape completion to model the objects…

We consider sketching algorithms which first quickly compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g., low rank approximation. In the learning-based…

Humans universally dislike the task of cleaning up a messy room. If machines were to help us with this task, they must understand human criteria for regular arrangements, such as several types of symmetry, co-linearity or co-circularity,…

State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are…

The ability to place objects in the environment is an important skill for a personal robot. An object should not only be placed stably, but should also be placed in its preferred location/orientation. For instance, a plate is preferred to…

A new method for the unsupervised learning of sparse representations using autoencoders is proposed and implemented by ordering the output of the hidden units by their activation value and progressively reconstructing the input in this…

A major challenge in scene graph classification is that the appearance of objects and relations can be significantly different from one image to another. Previous works have addressed this by relational reasoning over all objects in an…

General scene perception has progressed from object recognition toward open-vocabulary grounding, part localization, and affordance prediction. Yet these capabilities are often realized as isolated predictions that localize objects, parts,…

Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of nodes as objects and…

Pose estimation is a widely explored problem, enabling many robotic tasks such as grasping and manipulation. In this paper, we tackle the problem of pose estimation for objects that exhibit rotational symmetry, which are common in man-made…

The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places. It depends both on common-sense knowledge on the objective side and human user preference on the subjective side. In…

Placing objects is a fundamental task for domestic service robots (DSRs). Thus, inferring the collision-risk before a placing motion is crucial for achieving the requested task. This problem is particularly challenging because it is…

Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single object representation…

Scene graph generation models understand the scene through object and predicate recognition, but are prone to mistakes due to the challenges of perception in the wild. Perception errors often lead to nonsensical compositions in the output…

Object detection is essential to safe autonomous or assisted driving. Previous works usually utilize RGB images or LiDAR point clouds to identify and localize multiple objects in self-driving. However, cameras tend to fail in bad driving…

Visual localization is considered to be one of the crucial parts in many robotic and vision systems. While state-of-the art methods that relies on feature matching have proven to be accurate for visual localization, its requirements for…

This article presents a family of Stochastic Cartographic Occupancy Prediction Engines (SCOPEs) that enable mobile robots to predict the future states of complex dynamic environments. They do this by accounting for the motion of the robot…

We describe work to control graphics rendering under limited computational resources by taking a decision-theoretic perspective on perceptual costs and computational savings of approximations. The work extends earlier work on the control of…