Related papers: Learning Direct Optimization for Scene Understandi…

We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model…

The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct preference optimization (DPO) to enhance the alignment of…

Light detection and ranging (LiDAR)-inertial odometry (LIO) enables accurate localization and mapping for autonomous navigation in various scenes. However, its performance remains sensitive to variations in spatial scale, which refers to…

3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular…

There is a growing interest in the use of latent diffusion models (LDMs) for image restoration (IR) tasks due to their ability to model effectively the distribution of natural images. While significant progress has been made, there are…

This paper proposes and studies a detection technique for adversarial scenarios (dubbed deterministic detection). This technique provides an alternative detection methodology in case the usual stochastic methods are not applicable: this can…

We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain…

We analyze a learning-to-optimize (L2O) algorithm that exploits parameter space symmetry to enhance optimization efficiency. Prior work has shown that jointly learning symmetry transformations and local updates improves meta-optimizer…

Fine-tuning Vision-Language Models (VLMs) is a common strategy to improve performance following an ad-hoc data collection and annotation of real-world scenes. However, this process is often prone to biases, errors, and distribution…

Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive…

There exist numerous ways of representing 3D orientations. Each representation has both limitations and unique features. Choosing the best representation for one task is often a difficult chore, and there exist conflicting opinions on which…

Memory-efficient personalization is critical for adapting text-to-image diffusion models while preserving user privacy and operating within the limited computational resources of edge devices. To this end, we propose a selective…

We address the problem of estimating the inputs of a dynamical system from measurements of the system's outputs. To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the…

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In…

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central…

Finding an unsupervised decomposition of an image into individual objects is a key step to leverage compositionality and to perform symbolic reasoning. Traditionally, this problem is solved using amortized inference, which does not…

Video prediction is a crucial task for intelligent agents such as robots and autonomous vehicles, since it enables them to anticipate and act early on time-critical incidents. State-of-the-art video prediction methods typically model the…

Tokenizing images into compact visual representations is a key step in learning efficient and high-quality image generative models. We present a simple diffusion tokenizer (DiTo) that learns compact visual representations for image…

We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. It has excellent gradient approximation properties for the underlying…