分享

Monocular object pose estimation, as a pivotal task in computer vision and robotics, heavily depends on accurate 2D-3D correspondences, which often demand costly CAD models that may not be readily available. Object 3D reconstruction methods offer an alternative, among which recent advancements in 3D Gaussian Splatting (3DGS) afford a compelling potential. Yet its performance still suffers and tends to overfit with fewer input views. Embracing this challenge, we introduce SGPose, a novel framework for sparse view object pose estimation using Gaussian-based methods. Given as few as ten views, SGPose generates a geometric-aware representation by starting with a random cuboid initialization, eschewing reliance on Structure-from-Motion (SfM) pipeline-derived geometry as required by traditional 3DGS methods. SGPose removes the dependence on CAD models by regressing dense 2D-3D correspondences between images and the reconstructed model from sparse input and random initialization, while the geometric-consistent depth supervision and online synthetic view warping are key to the success. Experiments on typical benchmarks, especially on the Occlusion LM-O dataset, demonstrate that SGPose outperforms existing methods even under sparse view constraints, under-scoring its potential in real-world applications.

Estimating touch contact and pressure in egocentric vision is a central task for downstream applications in Augmented Reality, Virtual Reality, as well as many robotic applications, because it provides precise physical insights into hand-object interaction and object manipulation. However, existing contact pressure datasets lack egocentric views and hand poses, which are essential for accurate estimation during in-situ operation, both for AR/VR interaction and robotic manipulation. In this paper, we introduce EgoPressure,a novel dataset of touch contact and pressure interaction from an egocentric perspective, complemented with hand pose meshes and fine-grained pressure intensities for each contact. The hand poses in our dataset are optimized using our proposed multi-view sequence-based method that processes footage from our capture rig of 8 accurately calibrated RGBD cameras. EgoPressure comprises 5.0 hours of touch contact and pressure interaction from 21 participants captured by a moving egocentric camera and 7 stationary Kinect cameras, which provided RGB images and depth maps at 30 Hz. In addition, we provide baselines for estimating pressure with different modalities, which will enable future developments and benchmarking on the dataset. Overall, we demonstrate that pressure and hand poses are complementary, which supports our intention to better facilitate the physical understanding of hand-object interactions in AR/VR and robotics research.

Recent progress in image deblurring techniques focuses mainly on operating in both frequency and spatial domains using the Fourier transform (FT) properties. However, their performance is limited due to the dependency of FT on stationary signals and its lack of capability to extract spatial-frequency properties. In this paper, we propose a novel approach based on the Fractional Fourier Transform (FRFT), a unified spatial-frequency representation leveraging both spatial and frequency components simultaneously, making it ideal for processing non-stationary signals like images. Specifically, we introduce a Fractional Fourier Transformer (F2former), where we combine the classical fractional Fourier based Wiener deconvolution (F2WD) as well as a multi-branch encoder-decoder transformer based on a new fractional frequency aware transformer block (F2TB). We design F2TB consisting of a fractional frequency aware self-attention (F2SA) to estimate element-wise product attention based on important frequency components and a novel feed-forward network based on frequency division multiplexing (FM-FFN) to refine high and low frequency features separately for efficient latent clear image restoration. Experimental results for the cases of both motion deblurring as well as defocus deblurring show that the performance of our proposed method is superior to other state-of-the-art (SOTA) approaches.

Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images. Although State-Space Models, such as Mamba, are proficient in long-range modeling with linear complexity, most Mamba-based approaches use fixed scanning strategies, which can introduce biased prior information. To mitigate this issue, we propose a novel Bayesian-inspired scanning strategy called Random Shuffle, supplemented by an theoretically-feasible inverse shuffle to maintain information coordination invariance, aiming to eliminate biases associated with fixed sequence scanning. Based on this transformation pair, we customized the Shuffle Mamba Framework, penetrating modality-aware information representation and cross-modality information interaction across spatial and channel axes to ensure robust interaction and an unbiased global receptive field for multi-modal image fusion. Furthermore, we develop a testing methodology based on Monte-Carlo averaging to ensure the model's output aligns more closely with expected results. Extensive experiments across multiple multi-modal image fusion tasks demonstrate the effectiveness of our proposed method, yielding excellent fusion quality over state-of-the-art alternatives. Code will be available upon acceptance.

With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current large-scale multimodal models achieve this by mapping visual features obtained from the visual encoder into a large language model and using them as inputs alongside text for downstream tasks. Therefore, the number of visual tokens directly affects the training and inference speed of the model. There has been significant work on token pruning for visual transformers, but for large multimodal models, only relying on visual information for token pruning or compression may lead to significant loss of important information. On the other hand, the textual input in the form of a question may contain valuable information that can aid in answering the question, providing additional knowledge to the model. To address the potential oversimplification and excessive pruning that can occur with most purely visual token pruning methods, we propose a text information-guided dynamic visual token recovery mechanism that does not require training. This mechanism leverages the similarity between the question text and visual tokens to recover visually meaningful tokens with important text information while merging other less important tokens. Experimental results demonstrate that our proposed method achieves comparable performance to the original approach while compressing the visual tokens to an average of 10% of the original quantity. Our source code will be made publicly available following acceptance.

Recently, multimodal large language models (MM-LLMs) have achieved great success in many multimodal tasks, but their high computational costs limit their further promotion and application. In the MM-LLMs framework, the main computational consumption step is the processing of concatenated text and visual tokens at the LLM layer. The length of the input token for LLM directly affects the overall training and inference efficiency. In response to this issue, we further studied the visual tokens of MM-LLMs. We found that the similarity between visual and CLS tokens in the visual encoder follows a long-tail distribution. In other words, only a few visual tokens are highly similar to CLS tokens. Therefore, we designed a dynamic pruning algorithm to address this issue. Firstly, for different input samples, we search for the inflection point of their visual CLS token similarity curve and use it as the corresponding segmentation point to trim the visual markers. This process mainly reduces the output of the visual encoder to accelerate the model. Then, in the LLM layer, the concatenated visual text tokens are pruned for the second time. During this process, due to the interaction between visual and textual features, visual and textual tokens with low text correlation are further filtered, achieving a balance between efficiency and performance. The results on multiple datasets show that our proposed method can achieve performance that competes with the original performance when using an average of 22% of the original token quantity. Our source code will be made publicly available following acceptance.

Blind image deblurring is a challenging low-level vision task that involves estimating the unblurred image when the blur kernel is unknown. In this paper, we present a self-supervised multi-scale blind image deblurring method to jointly estimate the latent image and the blur kernel via alternating optimization. In the image estimation step, we construct a multi-scale generator network with multiple inputs and multiple outputs to collaboratively estimate latent images at various scales, supervised by an image pyramid constructed from only the blurred image. This generator places architectural constraints on the network and avoids the need for mathematical expression of image priors. In the blur kernel estimation step, the blur kernel at each scale is independently estimated with a direct solution to a quadratic regularized least-squares model for its flexible adaptation to the proposed multi-scale generator for image estimation. Thanks to the collaborative estimation across multiple scales, our method avoids the computationally intensive coarse-to-fine propagation and additional image deblurring processes used in traditional mathematical optimization-based methods. Quantitative and qualitative experimental results on synthetic and realistic datasets demonstrate the superior performance of our method, especially for handling large and real-world blurs.

The problem of cleaning a messy table using Deep Neural Networks is a very interesting problem in both social and industrial robotics. This project focuses on the social application of this technology. A neural network model that is capable of detecting and recognizing common tabletop objects, such as a mug, mouse, or stapler is developed. The model also predicts the angle at which these objects are placed on a table,with respect to some reference. Assuming each object has a fixed intended position and orientation on the tabletop, the orientation of a particular object predicted by the deep learning model can be used to compute the transformation matrix to move the object from its initial position to the intended position. This can be fed to a pick and place robot to carry out the transfer.This paper talks about the deep learning approaches used in this project for object detection and orientation estimation.

Human pose estimation (HPE) is crucial for various applications. However, deploying HPE algorithms in surveillance contexts raises significant privacy concerns due to the potential leakage of sensitive personal information (SPI) such as facial features, and ethnicity. Existing privacy-enhancing methods often compromise either privacy or performance, or they require costly additional modalities. We propose a novel privacy-enhancing system that generates privacy-enhanced portraits while maintaining high HPE performance. Our key innovations include the reversible recovery of SPI for authorized personnel and the preservation of contextual information. By jointly optimizing a privacy-enhancing module, a privacy recovery module, and a pose estimator, our system ensures robust privacy protection, efficient SPI recovery, and high-performance HPE. Experimental results demonstrate the system's robust performance in privacy enhancement, SPI recovery, and HPE.

Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large language models (LLMs). We propose \systemname{}, a novel neurosymbolic framework, to improve the robustness and reliability of LLMs in question-answering tasks. We provide \systemname{} with a domain-specific knowledge base, a logical reasoning system, and an integration to an existing LLM. This framework has two capabilities (1) context gathering: generating explainable and relevant context for a given query, and (2) validation: confirming and validating the factual accuracy of a statement in accordance with a knowledge base (KB). Our work opens a new area of neurosymbolic generative AI text validation and user personalization.

Reinforcement Learning (RL) plays a crucial role in aligning large language models (LLMs) with human preferences and improving their ability to perform complex tasks. However, current approaches either require significant computational resources due to the use of multiple models and extensive online sampling for training (e.g., PPO) or are framed as bandit problems (e.g., DPO, DRO), which often struggle with multi-step reasoning tasks, such as math problem-solving and complex reasoning that involve long chains of thought. To overcome these limitations, we introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model. The MDP formulation of DQO offers structural advantages over bandit-based methods, enabling more effective process supervision. Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through a carefully designed context extension stage, with the goal of producing generalist long-context capabilities. In our preliminary experiments, however, we discovered that the current open-weight generalist long-context models are still lacking in practical long-context processing tasks. While this means perfectly effective long-context modeling demands task-specific data, the cost can be prohibitive. In this paper, we draw inspiration from how humans process a large body of information: a lossy \textbf{retrieval} stage ranks a large set of documents while the reader ends up reading deeply only the top candidates. We build an \textbf{automatic} data synthesis pipeline that mimics this process using short-context LMs. The short-context LMs are further tuned using these self-generated data to obtain task-specific long-context capabilities. Similar to how pre-training learns from imperfect data, we hypothesize and further demonstrate that the short-context model can bootstrap over the synthetic data, outperforming not only long-context generalist models but also the retrieval and read pipeline used to synthesize the training data in real-world tasks such as long-context retrieval augmented generation.