Related papers: Diffusion-Augmented Depth Prediction with Sparse A…

Accident anticipation is essential for proactive and safe autonomous driving, where even a brief advance warning can enable critical evasive actions. However, two key challenges hinder real-world deployment: (1) noisy or degraded sensory…

This paper proposes a novel method for depth completion, which leverages multi-view improved monitored distillation to generate more precise depth maps. Our approach builds upon the state-of-the-art ensemble distillation method, in which we…

Recommendation systems often rely on implicit feedback, where only positive user-item interactions can be observed. Negative sampling is therefore crucial to provide proper negative training signals. However, existing methods tend to…

Motion prediction is a challenging problem in autonomous driving as it demands the system to comprehend stochastic dynamics and the multi-modal nature of real-world agent interactions. Diffusion models have recently risen to prominence, and…

Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…

Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by the out-of-distribution (OOD) extrapolation problem. Existing approaches typically…

3D object detection has become indispensable in the field of autonomous driving. To date, gratifying breakthroughs have been recorded in 3D object detection research, attributed to deep learning. However, deep learning algorithms are…

Monocular 3D object detection has achieved impressive performance on densely annotated datasets. However, it struggles when only a fraction of objects are labeled due to the high cost of 3D annotation. This sparsely annotated setting is…

The recent emergence of Distributed Acoustic Sensing (DAS) technology has facilitated the effective capture of traffic-induced seismic data. The traffic-induced seismic wave is a prominent contributor to urban vibrations and contain crucial…

Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks. However, existing regression-based methods…

As a critical task in autonomous driving perception systems, 3D object detection is used to identify and track key objects, such as vehicles and pedestrians. However, detecting distant, small, or occluded objects (hard instances) remains a…

Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance. While supervised methods are effective, they require extensive labeled data…

We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach,…

We present AnchorDP3, a diffusion policy framework for dual-arm robotic manipulation that achieves state-of-the-art performance in highly randomized environments. AnchorDP3 integrates three key innovations: (1) Simulator-Supervised Semantic…

Most successful approaches to estimate the 6D pose of an object typically train a neural network by supervising the learning with annotated poses in real world images. These annotations are generally expensive to obtain and a common…

Accurate ground truth annotations are critical to supervised learning and evaluating the performance of autonomous vehicle systems. These vehicles are typically equipped with active sensors, such as LiDAR, which scan the environment in…

Multi-modal 3D object detection has exhibited significant progress in recent years. However, most existing methods can hardly scale to long-range scenarios due to their reliance on dense 3D features, which substantially escalate…

Recent advances in robotic manipulation have highlighted the effectiveness of learning from demonstration. However, while end-to-end policies excel in expressivity and flexibility, they struggle both in generalizing to novel object…

This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1…

This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior works address this problem by simply adding a dense depth…