Search

We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based manner without additional computational overhead in learning. Experimental results on pubic benchmarks demonstrate the effectiveness of our approach., Comment: ECCV 2024

NeRF-based methods reconstruct 3D scenes by building a radiance field with implicit or explicit representations. While NeRF-based methods can perform novel view synthesis (NVS) at arbitrary scale, the performance in high-resolution novel view synthesis (HRNVS) with low-resolution (LR) optimization often results in oversmoothing. On the other hand, single-image super-resolution (SR) aims to enhance LR images to HR counterparts but lacks multi-view consistency. To address these challenges, we propose Arbitrary-Scale Super-Resolution NeRF (ASSR-NeRF), a novel framework for super-resolution novel view synthesis (SRNVS). We propose an attention-based VoxelGridSR model to directly perform 3D super-resolution (SR) on the optimized volume. Our model is trained on diverse scenes to ensure generalizability. For unseen scenes trained with LR views, we then can directly apply our VoxelGridSR to further refine the volume and achieve multi-view consistent SR. We demonstrate quantitative and qualitatively that the proposed method achieves significant performance in SRNVS.

Large language models (LLMs) have revolutionized Natural Language Processing (NLP) by minimizing the need for complex feature engineering. However, the application of LLMs in specialized domains like biopharmaceuticals and chemistry remains largely unexplored. These fields are characterized by intricate terminologies, specialized knowledge, and a high demand for precision areas where general purpose LLMs often fall short. In this study, we introduce PharmaGPT, a suite of domain specilized LLMs with 13 billion and 70 billion parameters, specifically trained on a comprehensive corpus tailored to the Bio-Pharmaceutical and Chemical domains. Our evaluation shows that PharmaGPT surpasses existing general models on specific-domain benchmarks such as NAPLEX, demonstrating its exceptional capability in domain-specific tasks. Remarkably, this performance is achieved with a model that has only a fraction, sometimes just one-tenth-of the parameters of general-purpose large models. This advancement establishes a new benchmark for LLMs in the bio-pharmaceutical and chemical fields, addressing the existing gap in specialized language modeling. It also suggests a promising path for enhanced research and development, paving the way for more precise and effective NLP applications in these areas.

In recent years, large language models(LLMs) have attracted significant attention due to their exceptional performance across a multitude of natural language process tasks, and have been widely applied in various fields. However, the application of large language models in the Intellectual Property (IP) domain is challenging due to the strong need for specialized knowledge, privacy protection, processing of extremely long text in this field. In this technical report, we present for the first time a low-cost, standardized procedure for training IP-oriented LLMs, meeting the unique requirements of the IP domain. Using this standard process, we have trained the PatentGPT series models based on open-source pretrained models. By evaluating them on the open-source IP-oriented benchmark MOZIP, our domain-specific LLMs outperforms GPT-4, indicating the effectiveness of the proposed training procedure and the expertise of the PatentGPT models in the IP domain. Remarkably, our model surpassed GPT-4 on the 2019 China Patent Agent Qualification Examination, scoring 65 and matching human expert levels. Additionally, the PatentGPT model, which utilizes the SMoE architecture, achieves performance comparable to that of GPT-4 in the IP domain and demonstrates a better cost-performance ratio on long-text tasks, potentially serving as an alternative to GPT-4 within the IP domain., Comment: 19 pages, 9 figures

We present a video decomposition method that facilitates layer-based editing of videos with spatiotemporally varying lighting and motion effects. Our neural model decomposes an input video into multiple layered representations, each comprising a 2D texture map, a mask for the original video, and a multiplicative residual characterizing the spatiotemporal variations in lighting conditions. A single edit on the texture maps can be propagated to the corresponding locations in the entire video frames while preserving other contents' consistencies. Our method efficiently learns the layer-based neural representations of a 1080p video in 25s per frame via coordinate hashing and allows real-time rendering of the edited result at 71 fps on a single GPU. Qualitatively, we run our method on various videos to show its effectiveness in generating high-quality editing effects. Quantitatively, we propose to adopt feature-tracking evaluation metrics for objectively assessing the consistency of video editing. Project page: https://lightbulb12294.github.io/hashing-nvd/

The volume and diversity of training data are critical for modern deep learningbased methods. Compared to the massive amount of labeled perspective images, 360 panoramic images fall short in both volume and diversity. In this paper, we propose PanoMixSwap, a novel data augmentation technique specifically designed for indoor panoramic images. PanoMixSwap explicitly mixes various background styles, foreground furniture, and room layouts from the existing indoor panorama datasets and generates a diverse set of new panoramic images to enrich the datasets. We first decompose each panoramic image into its constituent parts: background style, foreground furniture, and room layout. Then, we generate an augmented image by mixing these three parts from three different images, such as the foreground furniture from one image, the background style from another image, and the room structure from the third image. Our method yields high diversity since there is a cubical increase in image combinations. We also evaluate the effectiveness of PanoMixSwap on two indoor scene understanding tasks: semantic segmentation and layout estimation. Our experiments demonstrate that state-of-the-art methods trained with PanoMixSwap outperform their original setting on both tasks consistently., Comment: BMVC'23; project page:https://yuchenghsieh.github.io/PanoMixSwap

Recently, deception detection on human videos is an eye-catching techniques and can serve lots applications. AI model in this domain demonstrates the high accuracy, but AI tends to be a non-interpretable black box. We introduce an attention-aware neural network addressing challenges inherent in video data and deception dynamics. This model, through its continuous assessment of visual, audio, and text features, pinpoints deceptive cues. We employ a multimodal fusion strategy that enhances accuracy; our approach yields a 92\% accuracy rate on a real-life trial dataset. Most important of all, the model indicates the attention focus in the videos, providing valuable insights on deception cues. Hence, our method adeptly detects deceit and elucidates the underlying process. We further enriched our study with an experiment involving students answering questions either truthfully or deceitfully, resulting in a new dataset of 309 video clips, named ATSFace. Using this, we also introduced a calibration method, which is inspired by Low-Rank Adaptation (LoRA), to refine individual-based deception detection accuracy., Comment: 10 pages, 9 figures

We propose ImGeoNet, a multi-view image-based 3D object detection framework that models a 3D space by an image-induced geometry-aware voxel representation. Unlike previous methods which aggregate 2D features into 3D voxels without considering geometry, ImGeoNet learns to induce geometry from multi-view images to alleviate the confusion arising from voxels of free space, and during the inference phase, only images from multiple views are required. Besides, a powerful pre-trained 2D feature extractor can be leveraged by our representation, leading to a more robust performance. To evaluate the effectiveness of ImGeoNet, we conduct quantitative and qualitative experiments on three indoor datasets, namely ARKitScenes, ScanNetV2, and ScanNet200. The results demonstrate that ImGeoNet outperforms the current state-of-the-art multi-view image-based method, ImVoxelNet, on all three datasets in terms of detection accuracy. In addition, ImGeoNet shows great data efficiency by achieving results comparable to ImVoxelNet with 100 views while utilizing only 40 views. Furthermore, our studies indicate that our proposed image-induced geometry-aware representation can enable image-based methods to attain superior detection accuracy than the seminal point cloud-based method, VoteNet, in two practical scenarios: (1) scenarios where point clouds are sparse and noisy, such as in ARKitScenes, and (2) scenarios involve diverse object classes, particularly classes of small objects, as in the case in ScanNet200., Comment: ICCV'23; project page: https://ttaoretw.github.io/imgeonet/

Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the object has been a long-standing problem in computer vision and graphics. In this paper, we introduce an accurate and highly efficient object reconstruction pipeline combining neural based object reconstruction and physics-based inverse rendering (PBIR). Our pipeline firstly leverages a neural SDF based shape reconstruction to produce high-quality but potentially imperfect object shape. Then, we introduce a neural material and lighting distillation stage to achieve high-quality predictions for material and illumination. In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination. Experimental results demonstrate our pipeline significantly outperforms existing methods quality-wise and performance-wise., Comment: ICCV 2023. Project page at https://neural-pbir.github.io/ Update Stanford-ORB results

Nuclear materials are often demanded to function for extended time in extreme environments, including high radiation fluxes and transmutation, high temperature and temperature gradients, stresses, and corrosive coolants. They also have a wide range of microstructural and chemical makeup, with multifaceted and often out-of-equilibrium interactions. Machine learning (ML) is increasingly being used to tackle these complex time-dependent interactions and aid researchers in developing models and making predictions, sometimes with better accuracy than traditional modeling that focuses on one or two parameters at a time. Conventional practices of acquiring new experimental data in nuclear materials research are often slow and expensive, limiting the opportunity for data-centric ML, but new methods are changing that paradigm. Here we review high-throughput computational and experimental data approaches, especially robotic experimentation and active learning that based on Gaussian process and Bayesian optimization. We show ML examples in structural materials ( e.g., reactor pressure vessel (RPV) alloys and radiation detecting scintillating materials) and highlight new techniques of high-throughput sample preparation and characterizations, and automated radiation/environmental exposures and real-time online diagnostics. This review suggests that ML models of material constitutive relations in plasticity, damage, and even electronic and optical responses to radiation are likely to become powerful tools as they develop. Finally, we speculate on how the recent trends in artificial intelligence (AI) and machine learning will soon make the utilization of ML techniques as commonplace as the spreadsheet curve-fitting practices of today.

This paper aims to address a new task of image morphing under a multiview setting, which takes two sets of multiview images as the input and generates intermediate renderings that not only exhibit smooth transitions between the two input sets but also ensure visual consistency across different views at any transition state. To achieve this goal, we propose a novel approach called Multiview Regenerative Morphing that formulates the morphing process as an optimization to solve for rigid transformation and optimal-transport interpolation. Given the multiview input images of the source and target scenes, we first learn a volumetric representation that models the geometry and appearance for each scene to enable the rendering of novel views. Then, the morphing between the two scenes is obtained by solving optimal transport between the two volumetric representations in Wasserstein metrics. Our approach does not rely on user-specified correspondences or 2D/3D input meshes, and we do not assume any predefined categories of the source and target scenes. The proposed view-consistent interpolation scheme directly works on multiview images to yield a novel and visually plausible effect of multiview free-form morphing.

In this technical report, we improve the DVGO framework (called DVGOv2), which is based on Pytorch and uses the simplest dense grid representation. First, we re-implement part of the Pytorch operations with cuda, achieving 2-3x speedup. The cuda extension is automatically compiled just in time. Second, we extend DVGO to support Forward-facing and Unbounded Inward-facing capturing. Third, we improve the space time complexity of the distortion loss proposed by mip-NeRF 360 from O(N^2) to O(N). The distortion loss improves our quality and training speed. Our efficient implementation could allow more future works to benefit from the loss., Comment: Project page https://sunset1995.github.io/dvgo/ ; Code https://github.com/sunset1995/DirectVoxGO ; Results updated

A generalized Motzkin path, called G-Motzkin path for short, of length $n$ is a lattice path from $(0, 0)$ to $(n, 0)$ in the first quadrant of the XOY-plane that consists of up steps $\mathbf{u}=(1, 1)$, down steps $\mathbf{d}=(1, -1)$, horizontal steps $\mathbf{h}=(1, 0)$ and vertical steps $\mathbf{v}=(0, -1)$. An $(a,b,c)$-G-Motzkin path is a weighted G-Motzkin path such that the $\mathbf{u}$-steps, $\mathbf{h}$-steps, $\mathbf{v}$-steps and $\mathbf{d}$-steps are weighted respectively by $1, a, b$ and $c$. Let $\tau$ be a word on $\{\mathbf{u}, \mathbf{d}, \mathbf{v}, \mathbf{d}\}$, denoted by $\mathcal{G}_n^{\tau}(a,b,c)$ the set of $\tau$-avoiding $(a,b,c)$-G-Motzkin paths of length $n$ for a pattern $\tau$. In this paper, we consider the $\mathbf{uvv}$-avoiding $(a,b,c)$-G-Motzkin paths and provide a direct bijection $\sigma$ between $\mathcal{G}_n^{\mathbf{uvv}}(a,b,b^2)$ and $\mathcal{G}_n^{\mathbf{uvu}}(a,b,b^2)$. Finally, the set of fixed points of $\sigma$ is also described and counted., Comment: 11pages,2 figures. arXiv admin note: substantial text overlap with arXiv:2201.09236

We present the first self-supervised method to train panoramic room layout estimation models without any labeled data. Unlike per-pixel dense depth that provides abundant correspondence constraints, layout representation is sparse and topological, hindering the use of self-supervised reprojection consistency on images. To address this issue, we propose Differentiable Layout View Rendering, which can warp a source image to the target camera pose given the estimated layout from the target image. As each rendered pixel is differentiable with respect to the estimated layout, we can now train the layout estimation model by minimizing reprojection loss. Besides, we introduce regularization losses to encourage Manhattan alignment, ceiling-floor alignment, cycle consistency, and layout stretch consistency, which further improve our predictions. Finally, we present the first self-supervised results on ZilloIndoor and MatterportLayout datasets. Our approach also shows promising solutions in data-scarce scenarios and active learning, which would have an immediate value in the real estate virtual tour software. Code is available at https://github.com/joshua049/Stereo-360-Layout.