Related papers: Learning Direct Optimization for Scene Understandi…

Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the memory overhead of backpropagation. However, it converges slowly due to the inherent curse…

We show how to utilize machine learning approaches to improve sliding window algorithms for approximate frequency estimation problems, under the ``algorithms with predictions'' framework. In this dynamic environment, previous…

Current traditional methods for LiDAR-camera extrinsics estimation depend on offline targets and human efforts, while learning-based approaches resort to iterative refinement for calibration results, posing constraints on their…

The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods…

LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a…

In this work, we present LaserFlow, an efficient method for 3D object detection and motion forecasting from LiDAR. Unlike the previous work, our approach utilizes the native range view representation of the LiDAR, which enables our method…

Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on learning image representation combining local and global…

Real-time lane detection in embedded systems encounters significant challenges due to subtle and sparse visual signals in RGB images, often constrained by limited computational resources and power consumption. Although deep learning models…

We embark on a hitherto unreported problem of an autonomous robot (self-driving car) navigating in dynamic scenes in a manner that reduces its localization error and eventual cumulative drift or Absolute Trajectory Error, which is…

We present an algorithm that learns representations which explicitly compensate for domain mismatch and which can be efficiently realized as linear classifiers. Specifically, we form a linear transformation that maps features from the…

LiDAR odometry (LO) describes the task of finding an alignment of subsequent LiDAR point clouds. This alignment can be used to estimate the motion of the platform where the LiDAR sensor is mounted on. Currently, on the well-known KITTI…

Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Yet the role of ImageNet knowledge is seldom discussed despite…

Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…

3D scene graph prediction aims to abstract complex 3D environments into structured graphs consisting of objects and their pairwise relationships. Existing approaches typically adopt object-centric graph neural networks, where relation edge…

Edge robotics involves frequent exchanges of large-volume multi-modal data. Existing methods ignore the interdependency between robotic functionalities and communication conditions, leading to excessive communication overhead. This paper…

We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene. In contrast to previous work that relies on specialized image capture, user…

Recently, learning-based ego-motion estimation approaches have drawn strong interest from studies mostly focusing on visual perception. These groundbreaking works focus on unsupervised learning for odometry estimation but mostly for visual…

We develop an edge-assisted object recognition system with the aim of studying the system-level trade-offs between end-to-end latency and object recognition accuracy. We focus on developing techniques that optimize the transmission delay of…

Recent work in unsupervised representation learning has focused on learning deep directed latent-variable models. Fitting these models by maximizing the marginal likelihood or evidence is typically intractable, thus a common approximation…

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…